Minhui Xue

Pingyi Hu, Zihan Wang, Ruoxi Sun et al.

With the development of machine learning techniques, the attention of research has been moved from single-modal learning to multi-modal learning, as real-world data exist in the form of different modalities. However, multi-modal models often carry more information than single-modal models and they are usually applied in sensitive scenarios, such as medical report generation or disease identification. Compared with the existing membership inference against machine learning classifiers, we focus on the problem that the input and output of the multi-modal models are in different modalities, such as image captioning. This work studies the privacy leakage of multi-modal models through the lens of membership inference attack, a process of determining whether a data record involves in the model training process or not. To achieve this, we propose Multi-modal Models Membership Inference (M^4I) with two attack methods to infer the membership status, named metric-based (MB) M^4I and feature-based (FB) M^4I, respectively. More specifically, MB M^4I adopts similarity metrics while attacking to infer target data membership. FB M^4I uses a pre-trained shadow multi-modal feature extractor to achieve the purpose of data inference attack by comparing the similarities from extracted input and output features. Extensive experimental results show that both attack methods can achieve strong performances. Respectively, 72.5% and 94.83% of attack success rates on average can be obtained under unrestricted scenarios. Moreover, we evaluate multiple defense mechanisms against our attacks. The source code of M^4I attacks is publicly available at https://github.com/MultimodalMI/Multimodal-membership-inference.git.

Yingzi Ma, Zhengyue Zhao, Xiaogeng Liu et al.

Diffusion large language models (dLLMs) generate text by iteratively denoising partially masked sequences under bidirectional context, exposing a safety surface distinct from autoregressive LLMs. Because mask tokens are native inputs and tokens are committed by confidence rather than position, harmful content can be induced through infilling and outside the monitored prefix. Existing jailbreaks either miss this native infill capability or rely on low-diversity mask-bearing templates applied uniformly across goals, with little structural adaptation or accumulated attack experience. We propose MaskForge, a fully black-box adaptive attack that casts dLLM red-teaming as optimized search over a growing library of structural patterns. MaskForge abstracts successful attempts into reusable schemas, selects goal-compatible patterns with a UCB bandit, and invokes a scorer-guided fallback when the current library fails. Successful attempts are distilled back into the pattern library, enabling experience to accumulate across goals. Across five public dLLMs and three benchmarks, MaskForge achieves an average attack success rate of 79.3%, a 17.6% relative improvement over the strongest competing dLLM baseline. The matured pattern library further transfers to AdvBench without any updates, achieving a 88.2% attack success rate and a 67% relative improvement over the strongest competing baseline.

Wanlun Ma, Derui Wang, Ruoxi Sun et al.

Deep Neural Networks (DNNs) are susceptible to backdoor attacks during training. The model corrupted in this way functions normally, but when triggered by certain patterns in the input, produces a predefined target label. Existing defenses usually rely on the assumption of the universal backdoor setting in which poisoned samples share the same uniform trigger. However, recent advanced backdoor attacks show that this assumption is no longer valid in dynamic backdoors where the triggers vary from input to input, thereby defeating the existing defenses. In this work, we propose a novel technique, Beatrix (backdoor detection via Gram matrix). Beatrix utilizes Gram matrix to capture not only the feature correlations but also the appropriately high-order information of the representations. By learning class-conditional statistics from activation patterns of normal samples, Beatrix can identify poisoned samples by capturing the anomalies in activation patterns. To further improve the performance in identifying target labels, Beatrix leverages kernel-based testing without making any prior assumptions on representation distribution. We demonstrate the effectiveness of our method through extensive evaluation and comparison with state-of-the-art defensive techniques. The experimental results show that our approach achieves an F1 score of 91.1% in detecting dynamic backdoors, while the state of the art can only reach 36.9%.

Shuo Wang, Sharif Abuadbba, Sidharth Agarwal et al.

Existing integrity verification approaches for deep models are designed for private verification (i.e., assuming the service provider is honest, with white-box access to model parameters). However, private verification approaches do not allow model users to verify the model at run-time. Instead, they must trust the service provider, who may tamper with the verification results. In contrast, a public verification approach that considers the possibility of dishonest service providers can benefit a wider range of users. In this paper, we propose PublicCheck, a practical public integrity verification solution for services of run-time deep models. PublicCheck considers dishonest service providers, and overcomes public verification challenges of being lightweight, providing anti-counterfeiting protection, and having fingerprinting samples that appear smooth. To capture and fingerprint the inherent prediction behaviors of a run-time model, PublicCheck generates smoothly transformed and augmented encysted samples that are enclosed around the model's decision boundary while ensuring that the verification queries are indistinguishable from normal queries. PublicCheck is also applicable when knowledge of the target model is limited (e.g., with no knowledge of gradients or model parameters). A thorough evaluation of PublicCheck demonstrates the strong capability for model integrity breach detection (100% detection accuracy with less than 10 black-box API queries) against various model integrity attacks and model compression attacks. PublicCheck also demonstrates the smooth appearance, feasibility, and efficiency of generating a plethora of encysted samples for fingerprinting.

Haonan Zhong, Jiamin Chang, Ziyue Yang et al.

Generative AI (e.g., Generative Adversarial Networks - GANs) has become increasingly popular in recent years. However, Generative AI introduces significant concerns regarding the protection of Intellectual Property Rights (IPR) (resp. model accountability) pertaining to images (resp. toxic images) and models (resp. poisoned models) generated. In this paper, we propose an evaluation framework to provide a comprehensive overview of the current state of the copyright protection measures for GANs, evaluate their performance across a diverse range of GAN architectures, and identify the factors that affect their performance and future research directions. Our findings indicate that the current IPR protection methods for input images, model watermarking, and attribution networks are largely satisfactory for a wide range of GANs. We highlight that further attention must be directed towards protecting training sets, as the current approaches fail to provide robust IPR protection and provenance tracing on training sets.

Hua Ma, Shang Wang, Yansong Gao et al.

All current backdoor attacks on deep learning (DL) models fall under the category of a vertical class backdoor (VCB) -- class-dependent. In VCB attacks, any sample from a class activates the implanted backdoor when the secret trigger is present. Existing defense strategies overwhelmingly focus on countering VCB attacks, especially those that are source-class-agnostic. This narrow focus neglects the potential threat of other simpler yet general backdoor types, leading to false security implications. This study introduces a new, simple, and general type of backdoor attack coined as the horizontal class backdoor (HCB) that trivially breaches the class dependence characteristic of the VCB, bringing a fresh perspective to the community. HCB is now activated when the trigger is presented together with an innocuous feature, regardless of class. For example, the facial recognition model misclassifies a person who wears sunglasses with a smiling innocuous feature into the targeted person, such as an administrator, regardless of which person. The key is that these innocuous features are horizontally shared among classes but are only exhibited by partial samples per class. Extensive experiments on attacking performance across various tasks, including MNIST, facial recognition, traffic sign recognition, object detection, and medical diagnosis, confirm the high efficiency and effectiveness of the HCB. We rigorously evaluated the evasiveness of the HCB against a series of eleven representative countermeasures, including Fine-Pruning (RAID 18'), STRIP (ACSAC 19'), Neural Cleanse (Oakland 19'), ABS (CCS 19'), Februus (ACSAC 20'), NAD (ICLR 21'), MNTD (Oakland 21'), SCAn (USENIX SEC 21'), MOTH (Oakland 22'), Beatrix (NDSS 23'), and MM-BD (Oakland 24'). None of these countermeasures prove robustness, even when employing a simplistic trigger, such as a small and static white-square patch.

Huajie Chen, Tianqing Zhu, Lefeng Zhang et al.

Model extraction attacks currently pose a non-negligible threat to the security and privacy of deep learning models. By querying the model with a small dataset and usingthe query results as the ground-truth labels, an adversary can steal a piracy model with performance comparable to the original model. Two key issues that cause the threat are, on the one hand, accurate and unlimited queries can be obtained by the adversary; on the other hand, the adversary can aggregate the query results to train the model step by step. The existing defenses usually employ model watermarking or fingerprinting to protect the ownership. However, these methods cannot proactively prevent the violation from happening. To mitigate the threat, we propose QUEEN (QUEry unlEarNing) that proactively launches counterattacks on potential model extraction attacks from the very beginning. To limit the potential threat, QUEEN has sensitivity measurement and outputs perturbation that prevents the adversary from training a piracy model with high performance. In sensitivity measurement, QUEEN measures the single query sensitivity by its distance from the center of its cluster in the feature space. To reduce the learning accuracy of attacks, for the highly sensitive query batch, QUEEN applies query unlearning, which is implemented by gradient reverse to perturb the softmax output such that the piracy model will generate reverse gradients to worsen its performance unconsciously. Experiments show that QUEEN outperforms the state-of-the-art defenses against various model extraction attacks with a relatively low cost to the model accuracy. The artifact is publicly available at https://anonymous.4open.science/r/queen implementation-5408/.

Zhisheng Zhang, Derui Wang, Yifan Mi et al.

Recent advancements in speech synthesis technology have enriched our daily lives, with high-quality and human-like audio widely adopted across real-world applications. However, malicious exploitation like voice-cloning fraud poses severe security risks. Existing defense techniques struggle to address the production large language model (LLM)-based speech synthesis. While previous studies have considered the protection for fine-tuning synthesizers, they assume manually annotated transcripts. Given the labor intensity of manual annotation, end-to-end (E2E) systems leveraging automatic speech recognition (ASR) to generate transcripts are becoming increasingly prevalent, e.g., voice cloning via commercial APIs. Therefore, this E2E speech synthesis also requires new security mechanisms. To tackle these challenges, we propose E2E-VGuard, a proactive defense framework for two emerging threats: (1) production LLM-based speech synthesis, and (2) the novel attack arising from ASR-driven E2E scenarios. Specifically, we employ the encoder ensemble with a feature extractor to protect timbre, while ASR-targeted adversarial examples disrupt pronunciation. Moreover, we incorporate the psychoacoustic model to ensure perturbative imperceptibility. For a comprehensive evaluation, we test 16 open-source synthesizers and 3 commercial APIs across Chinese and English datasets, confirming E2E-VGuard's effectiveness in timbre and pronunciation protection. Real-world deployment validation is also conducted. Our code and demo page are available at https://wxzyd123.github.io/e2e-vguard/.

Weifei Jin, Yuxin Cao, Junjie Su et al.

Recent advances in Audio-Language Models (ALMs) have significantly improved multimodal understanding capabilities. However, the introduction of the audio modality also brings new and unique vulnerability vectors. Previous studies have proposed jailbreak attacks that specifically target ALMs, revealing that defenses directly transferred from traditional audio adversarial attacks or text-based Large Language Model (LLM) jailbreaks are largely ineffective against these ALM-specific threats. To address this issue, we propose ALMGuard, the first defense framework tailored to ALMs. Based on the assumption that safety-aligned shortcuts naturally exist in ALMs, we design a method to identify universal Shortcut Activation Perturbations (SAPs) that serve as triggers that activate the safety shortcuts to safeguard ALMs at inference time. To better sift out effective triggers while preserving the model's utility on benign tasks, we further propose Mel-Gradient Sparse Mask (M-GSM), which restricts perturbations to Mel-frequency bins that are sensitive to jailbreaks but insensitive to speech understanding. Both theoretical analyses and empirical results demonstrate the robustness of our method against both seen and unseen attacks. Overall, \MethodName reduces the average success rate of advanced ALM-specific jailbreak attacks to 4.6% across four models, while maintaining comparable utility on benign benchmarks, establishing it as the new state of the art. Our code and data are available at https://github.com/WeifeiJin/ALMGuard.

Zhenlin Xu, Xiaogang Zhu, Yu Yao et al.

Modern agentic systems allow Large Language Model (LLM) agents to tackle complex tasks through extensive tool usage, forming structured control flows of tool selection and execution. Existing security analyses often treat these control flows as ephemeral, one-off sessions, overlooking the persistent influence of memory. This paper identifies a new threat from Memory Control Flow Attacks (MCFA) that memory retrieval can dominate the control flow, forcing unintended tool usage even against explicit user instructions and inducing persistent behavioral deviations across tasks. To understand the impact of this vulnerability, we further design MEMFLOW, an automated evaluation framework that systematically identifies and quantifies MCFA across heterogeneous tasks and long interaction horizons. To evaluate MEMFLOW, we attack state-of-the-art LLMs, including GPT-5 mini, Claude Sonnet 4.5 and Gemini 2.5 Flash on real-world tools from two major LLM agent development frameworks, LangChain and LlamaIndex. The results show that in general over 90% trials are vulnerable to MCFA even under strict safety constraints, highlighting critical security risks that demand immediate attention.

Minhui Xue, Surya Nepal, Ling Liu et al.

This paper plans to develop an Equitable and Responsible AI framework with enabling techniques and algorithms for the Internet of Energy (IoE), in short, RAI4IoE. The energy sector is going through substantial changes fueled by two key drivers: building a zero-carbon energy sector and the digital transformation of the energy infrastructure. We expect to see the convergence of these two drivers resulting in the IoE, where renewable distributed energy resources (DERs), such as electric cars, storage batteries, wind turbines and photovoltaics (PV), can be connected and integrated for reliable energy distribution by leveraging advanced 5G-6G networks and AI technology. This allows DER owners as prosumers to participate in the energy market and derive economic incentives. DERs are inherently asset-driven and face equitable challenges (i.e., fair, diverse and inclusive). Without equitable access, privileged individuals, groups and organizations can participate and benefit at the cost of disadvantaged groups. The real-time management of DER resources not only brings out the equity problem to the IoE, it also collects highly sensitive location, time, activity dependent data, which requires to be handled responsibly (e.g., privacy, security and safety), for AI-enhanced predictions, optimization and prioritization services, and automated management of flexible resources. The vision of our project is to ensure equitable participation of the community members and responsible use of their data in IoE so that it could reap the benefits of advances in AI to provide safe, reliable and sustainable energy services.

Zhiyu Zhu, Huaming Chen, Jiayu Zhang et al.

To better understand the output of deep neural networks (DNN), attribution based methods have been an important approach for model interpretability, which assign a score for each input dimension to indicate its importance towards the model outcome. Notably, the attribution methods use the axioms of sensitivity and implementation invariance to ensure the validity and reliability of attribution results. Yet, the existing attribution methods present challenges for effective interpretation and efficient computation. In this work, we introduce MFABA, an attribution algorithm that adheres to axioms, as a novel method for interpreting DNN. Additionally, we provide the theoretical proof and in-depth analysis for MFABA algorithm, and conduct a large scale experiment. The results demonstrate its superiority by achieving over 101.5142 times faster speed than the state-of-the-art attribution algorithms. The effectiveness of MFABA is thoroughly evaluated through the statistical analysis in comparison to other methods, and the full implementation package is open-source at: https://github.com/LMBTough/MFABA

Jiamin Chang, Minhui Xue, Ruoxi Sun et al.

Recent advances in embodied Vision-Language Agentic Systems (VLAS), powered by large vision-language models (LVLMs), enable AI systems to perceive and reason over real-world scenes. Within this context, environmental signals such as traffic lights are essential in-band signals that can and should influence agent behavior. However, similar signals could also be crafted to operate as misleading visual injections, overriding user intent and posing security risks. This duality creates a fundamental challenge: agents must respond to legitimate environmental cues while remaining robust to misleading ones. We refer to this tension as trust boundary confusion. To study this behavior, we design a dual-intent dataset and evaluation framework, through which we show that current LVLM-based agents fail to reliably balance this trade-off, either ignoring useful signals or following harmful ones. We systematically evaluate 7 LVLM agents across multiple embodied settings under both structure-based and noise-based visual injections. To address these vulnerabilities, we propose a multi-agent defense framework that separates perception from decision-making to dynamically assess the reliability of visual inputs. Our approach significantly reduces misleading behaviors while preserving correct responses and provides robustness guarantees under adversarial perturbations. The code of the evaluation framework and artifacts are made available at https://anonymous.4open.science/r/Visual-Prompt-Inject.

Yutao Luo, Haotian Zhu, Shuchao Pang et al.

The rapid adoption of mobile graphical user interface (GUI) agents, which autonomously control applications and operating systems (OS), exposes new system-level attack surfaces. Existing backdoors against web GUI agents and general GenAI models rely on environmental injection or deceptive pop-ups to mislead the agent operation. However, these techniques do not work on screenshots-based mobile GUI agents due to the challenges of restricted trigger design spaces, OS background interference, and conflicts in multiple trigger-action mappings. We propose AgentRAE, a novel backdoor attack capable of inducing Remote Action Execution in mobile GUI agents using visually natural triggers (e.g., benign app icons in notifications). To address the underfitting caused by natural triggers and achieve accurate multi-target action redirection, we design a novel two-stage pipeline that first enhances the agent's sensitivity to subtle iconographic differences via contrastive learning, and then associates each trigger with a specific mobile GUI agent action through a backdoor post-training. Our extensive evaluation reveals that the proposed backdoor preserves clean performance with an attack success rate of over 90% across ten mobile operations. Furthermore, it is hard to visibly detect the benign-looking triggers and circumvents eight representative state-of-the-art defenses. These results expose an overlooked backdoor vector in mobile GUI agents, underscoring the need for defenses that scrutinize notification-conditioned behaviors and internal agent representations.

Yuxin Cao, Yumeng Zhu, Derui Wang et al.

Face recognition pipelines have been widely deployed in various mission-critical systems in trust, equitable and responsible AI applications. However, the emergence of adversarial attacks has threatened the security of the entire recognition pipeline. Despite the sheer number of attack methods proposed for crafting adversarial examples in both digital and physical forms, it is never an easy task to assess the real threat level of different attacks and obtain useful insight into the key risks confronted by face recognition systems. Traditional attacks view imperceptibility as the most important measurement to keep perturbations stealthy, while we suspect that industry professionals may possess a different opinion. In this paper, we delve into measuring the threat brought about by adversarial attacks from the perspectives of the industry and the applications of face recognition. In contrast to widely studied sophisticated attacks in the field, we propose an effective yet easy-to-launch physical adversarial attack, named AdvColor, against black-box face recognition pipelines in the physical world. AdvColor fools models in the recognition pipeline via directly supplying printed photos of human faces to the system under adversarial illuminations. Experimental results show that physical AdvColor examples can achieve a fooling rate of more than 96% against the anti-spoofing model and an overall attack success rate of 88% against the face recognition pipeline. We also conduct a survey on the threats of prevailing adversarial attacks, including AdvColor, to understand the gap between the machine-measured and human-assessed threat levels of different forms of adversarial attacks. The survey results surprisingly indicate that, compared to deliberately launched imperceptible attacks, perceptible but accessible attacks pose more lethal threats to real-world commercial systems of face recognition.

Yuxin Cao, Yian Li, Yumeng Zhu et al.

Anti-spoofing detection has become a necessity for face recognition systems due to the security threat posed by spoofing attacks. Despite great success in traditional attacks, most deep-learning-based methods perform poorly in 3D masks, which can highly simulate real faces in appearance and structure, suffering generalizability insufficiency while focusing only on the spatial domain with single frame input. This has been mitigated by the recent introduction of a biomedical technology called rPPG (remote photoplethysmography). However, rPPG-based methods are sensitive to noisy interference and require at least one second (> 25 frames) of observation time, which induces high computational overhead. To address these challenges, we propose a novel 3D mask detection framework, called FASTEN (Flow-Attention-based Spatio-Temporal aggrEgation Network). We tailor the network for focusing more on fine-grained details in large movements, which can eliminate redundant spatio-temporal feature interference and quickly capture splicing traces of 3D masks in fewer frames. Our proposed network contains three key modules: 1) a facial optical flow network to obtain non-RGB inter-frame flow information; 2) flow attention to assign different significance to each frame; 3) spatio-temporal aggregation to aggregate high-level spatial features and temporal transition features. Through extensive experiments, FASTEN only requires five frames of input and outperforms eight competitors for both intra-dataset and cross-dataset evaluations in terms of multiple detection metrics. Moreover, FASTEN has been deployed in real-world mobile devices for practical 3D mask detection.

Derui Wang, Kristen Moore, Diksha Goel et al.

Deep reinforcement learning (DRL) has gained widespread adoption in control and decision-making tasks due to its strong performance in dynamic environments. However, DRL agents are vulnerable to noisy observations and adversarial attacks, and concerns about the adversarial robustness of DRL systems have emerged. Recent efforts have focused on addressing these robustness issues by establishing rigorous theoretical guarantees for the returns achieved by DRL agents in adversarial settings. Among these approaches, policy smoothing has proven to be an effective and scalable method for certifying the robustness of DRL agents. Nevertheless, existing certifiably robust DRL relies on policies trained with simple Gaussian augmentations, resulting in a suboptimal trade-off between certified robustness and certified return. To address this issue, we introduce a novel paradigm dubbed \texttt{C}ertified-r\texttt{A}dius-\texttt{M}aximizing \texttt{P}olicy (\texttt{CAMP}) training. \texttt{CAMP} is designed to enhance DRL policies, achieving better utility without compromising provable robustness. By leveraging the insight that the global certified radius can be derived from local certified radii based on training-time statistics, \texttt{CAMP} formulates a surrogate loss related to the local certified radius and optimizes the policy guided by this surrogate loss. We also introduce \textit{policy imitation} as a novel technique to stabilize \texttt{CAMP} training. Experimental results demonstrate that \texttt{CAMP} significantly improves the robustness-return trade-off across various tasks. Based on the results, \texttt{CAMP} can achieve up to twice the certified expected return compared to that of baselines. Our code is available at https://github.com/NeuralSec/camp-robust-rl.

Mengying Zhang, Derui Wang, Ruoxi Sun et al.

Advanced model dememorization methods, including availability poisoning (unlearnability) and machine unlearning, are emerging as key safeguards against data misuse in machine learning (ML). At the training stage, unlearnability embeds imperceptible perturbations into data before release to reduce learnability. At the post-training stage, unlearning removes previously acquired information from models to prevent unauthorized disclosure or use. While both defenses aim to preserve the right to withhold knowledge, their vulnerabilities and shared foundations remain unclear. Specifically, both unlearnability and unlearning suffer from issues such as shallow dememorization, leading to falsely claimed data learnability reduction or forgetting in the presence of weight perturbations. Moreover, input perturbations may affect the effectiveness of downstream unlearning, while unlearning may inadvertently recover domain knowledge hidden by unlearnability. This interplay calls for deeper investigation. Finally, there is a lack of formal guarantees to provide theoretical insights into current defenses against shallow dememorization. In this Systematization of Knowledge, we present the first integrated analysis of model dememorization approaches leveraging unlearnability and unlearning. Our contributions are threefold: (i) a unified taxonomy of unlearnability and scalable unlearning methods; (ii) an empirical evaluation revealing the robustness, interplay, and shallow dememorization of leading methods; and (iii) the first theoretical guarantee on dememorization depth for models processed through certified unlearning. These results lay the foundation for unifying dememorization mechanisms across the ML lifecycle to achieve a deeper immemor state for sensitive knowledge.

Mengsha Kou, Xiaoyu Xia, Ziqi Wang et al.

Large Language Models (LLMs) increasingly underpin intelligent web applications, from chatbots to search and recommendation, where efficient specialization is essential. Low-Rank Adaptation (LoRA) enables such adaptation with minimal overhead, while federated LoRA allows web service providers to fine-tune shared models without data sharing. However, in privacy-sensitive deployments, clients inject varying levels of differential privacy (DP) noise, creating privacy heterogeneity that misaligns individual incentives and global performance. In this paper, we propose WinFLoRA, a privacy-heterogeneous federated LoRA that utilizes aggregation weights as incentives with noise awareness. Specifically, the noises from clients are estimated based on the uploaded LoRA adapters. A larger weight indicates greater influence on the global model and better downstream task performance, rewarding lower-noise contributions. By up-weighting low-noise updates, WinFLoRA improves global accuracy while accommodating clients' heterogeneous privacy requirements. Consequently, WinFLoRA aligns heterogeneous client utility in terms of privacy and downstream performance with global model objectives without third-party involvement. Extensive evaluations demonstrate that across multiple LLMs and datasets, WinFLoRA achieves up to 52.58% higher global accuracy and up to 2.56x client utility than state-of-the-art benchmarks. Source code is publicly available at https://github.com/koums24/WinFLoRA.git.

Zhongzheng Lai, Huaming Chen, Ruoxi Sun et al.

The security guarantee of AI-enabled software systems (particularly using deep learning techniques as a functional core) is pivotal against the adversarial attacks exploiting software vulnerabilities. However, little attention has been paid to a systematic investigation of vulnerabilities in such systems. A common situation learned from the open source software community is that deep learning engineers frequently integrate off-the-shelf or open-source learning frameworks into their ecosystems. In this work, we specifically look into deep learning (DL) framework and perform the first systematic study of vulnerabilities in DL systems through a comprehensive analysis of identified vulnerabilities from Common Vulnerabilities and Exposures (CVE) and open-source DL tools, including TensorFlow, Caffe, OpenCV, Keras, and PyTorch. We propose a two-stream data analysis framework to explore vulnerability patterns from various databases. We investigate the unique DL frameworks and libraries development ecosystems that appear to be decentralized and fragmented. By revisiting the Common Weakness Enumeration (CWE) List, which provides the traditional software vulnerability related practices, we observed that it is more challenging to detect and fix the vulnerabilities throughout the DL systems lifecycle. Moreover, we conducted a large-scale empirical study of 3,049 DL vulnerabilities to better understand the patterns of vulnerability and the challenges in fixing them. We have released the full replication package at https://github.com/codelzz/Vulnerabilities4DLSystem. We anticipate that our study can advance the development of secure DL systems.

Ruoxi Sun, Minhui Xue, Gareth Tyson et al.

Numerous open-source and commercial malware detectors are available. However, their efficacy is threatened by new adversarial attacks, whereby malware attempts to evade detection, e.g., by performing feature-space manipulation. In this work, we propose an explainability-guided and model-agnostic testing framework for robustness of malware detectors when confronted with adversarial attacks. The framework introduces the concept of Accrued Malicious Magnitude (AMM) to identify which malware features could be manipulated to maximize the likelihood of evading detection. We then use this framework to test several state-of-the-art malware detectors' abilities to detect manipulated malware. We find that (i) commercial antivirus engines are vulnerable to AMM-guided test cases; (ii) the ability of a manipulated malware generated using one detector to evade detection by another detector (i.e., transferability) depends on the overlap of features with large AMM values between the different detectors; and (iii) AMM values effectively measure the fragility of features (i.e., capability of feature-space manipulation to flip the prediction results) and explain the robustness of malware detectors facing evasion attacks. Our findings shed light on the limitations of current malware detectors, as well as how they can be improved.

Boming Xia, Liming Zhu, Erdun Gao et al.

Uncertainty in large language model (LLM)-based systems is often studied at the level of a single model output, yet deployed LLM applications are compound systems in which uncertainty is transformed and reused across model internals, workflow stages, component boundaries, persistent state, and human or organisational processes. Without principled treatment of how uncertainty is carried and reused across these boundaries, early errors can propagate and compound in ways that are difficult to detect and govern. This paper develops a systems-level account of uncertainty propagation. It introduces a conceptual framing for characterising propagated uncertainty signals, presents a structured taxonomy spanning intra-model (P1), system-level (P2), and socio-technical (P3) propagation mechanisms, synthesises cross-cutting engineering insights, and identifies five open research challenges.

Bang Wu, He Zhang, Xiangwen Yang et al.

The emergence of Graph Neural Networks (GNNs) in graph data analysis and their deployment on Machine Learning as a Service platforms have raised critical concerns about data misuse during model training. This situation is further exacerbated due to the lack of transparency in local training processes, potentially leading to the unauthorized accumulation of large volumes of graph data, thereby infringing on the intellectual property rights of data owners. Existing methodologies often address either data misuse detection or mitigation, and are primarily designed for local GNN models rather than cloud-based MLaaS platforms. These limitations call for an effective and comprehensive solution that detects and mitigates data misuse without requiring exact training data while respecting the proprietary nature of such data. This paper introduces a pioneering approach called GraphGuard, to tackle these challenges. We propose a training-data-free method that not only detects graph data misuse but also mitigates its impact via targeted unlearning, all without relying on the original training data. Our innovative misuse detection technique employs membership inference with radioactive data, enhancing the distinguishability between member and non-member data distributions. For mitigation, we utilize synthetic graphs that emulate the characteristics previously learned by the target model, enabling effective unlearning even in the absence of exact graph data. We conduct comprehensive experiments utilizing four real-world graph datasets to demonstrate the efficacy of GraphGuard in both detection and unlearning. We show that GraphGuard attains a near-perfect detection rate of approximately 100% across these datasets with various GNN models. In addition, it performs unlearning by eliminating the impact of the unlearned graph with a marginal decrease in accuracy (less than 5%).

Dayong Ye, Tianqing Zhu, Congcong Zhu et al.

Machine unlearning refers to the process of mitigating the influence of specific training data on machine learning models based on removal requests from data owners. However, one important area that has been largely overlooked in the research of unlearning is reinforcement learning. Reinforcement learning focuses on training an agent to make optimal decisions within an environment to maximize its cumulative rewards. During the training, the agent tends to memorize the features of the environment, which raises a significant concern about privacy. As per data protection regulations, the owner of the environment holds the right to revoke access to the agent's training data, thus necessitating the development of a novel and pressing research field, known as \emph{reinforcement unlearning}. Reinforcement unlearning focuses on revoking entire environments rather than individual data samples. This unique characteristic presents three distinct challenges: 1) how to propose unlearning schemes for environments; 2) how to avoid degrading the agent's performance in remaining environments; and 3) how to evaluate the effectiveness of unlearning. To tackle these challenges, we propose two reinforcement unlearning methods. The first method is based on decremental reinforcement learning, which aims to erase the agent's previously acquired knowledge gradually. The second method leverages environment poisoning attacks, which encourage the agent to learn new, albeit incorrect, knowledge to remove the unlearning environment. Particularly, to tackle the third challenge, we introduce the concept of ``environment inference attack'' to evaluate the unlearning outcomes.

Xiaoyu Xia, Ziqi Wang, Ruoxi Sun et al.

The right to be forgotten mandates that machine learning models enable the erasure of a data owner's data and information from a trained model. Removing data from the dataset alone is inadequate, as machine learning models can memorize information from the training data, increasing the potential privacy risk to users. To address this, multiple machine unlearning techniques have been developed and deployed. Among them, approximate unlearning is a popular solution, but recent studies report that its unlearning effectiveness is not fully guaranteed. Another approach, exact unlearning, tackles this issue by discarding the data and retraining the model from scratch, but at the cost of considerable computational and memory resources. However, not all devices have the capability to perform such retraining. In numerous machine learning applications, such as edge devices, Internet-of-Things (IoT), mobile devices, and satellites, resources are constrained, posing challenges for deploying existing exact unlearning methods. In this study, we propose a Constraint-aware Adaptive Exact Unlearning System at the network Edge (CAUSE), an approach to enabling exact unlearning on resource-constrained devices. Aiming to minimize the retrain overhead by storing sub-models on the resource-constrained device, CAUSE innovatively applies a Fibonacci-based replacement strategy and updates the number of shards adaptively in the user-based data partition process. To further improve the effectiveness of memory usage, CAUSE leverages the advantage of model pruning to save memory via compression with minimal accuracy sacrifice. The experimental results demonstrate that CAUSE significantly outperforms other representative systems in realizing exact unlearning on the resource-constrained device by 9.23%-80.86%, 66.21%-83.46%, and 5.26%-194.13% in terms of unlearning speed, energy consumption, and accuracy.

Yuxin Cao, Ziyu Zhao, Xi Xiao et al.

Video recognition systems are vulnerable to adversarial examples. Recent studies show that style transfer-based and patch-based unrestricted perturbations can effectively improve attack efficiency. These attacks, however, face two main challenges: 1) Adding large stylized perturbations to all pixels reduces the naturalness of the video and such perturbations can be easily detected. 2) Patch-based video attacks are not extensible to targeted attacks due to the limited search space of reinforcement learning that has been widely used in video attacks recently. In this paper, we focus on the video black-box setting and propose a novel attack framework named LogoStyleFool by adding a stylized logo to the clean video. We separate the attack into three stages: style reference selection, reinforcement-learning-based logo style transfer, and perturbation optimization. We solve the first challenge by scaling down the perturbation range to a regional logo, while the second challenge is addressed by complementing an optimization stage after reinforcement learning. Experimental results substantiate the overall superiority of LogoStyleFool over three state-of-the-art patch-based attacks in terms of attack performance and semantic preservation. Meanwhile, LogoStyleFool still maintains its performance against two existing patch-based defense methods. We believe that our research is beneficial in increasing the attention of the security community to such subregional style transfer attacks.

Shuchao Pang, Zhigang Lu, Haichen Wang et al.

Differential privacy (DP) is the de facto privacy standard against privacy leakage attacks, including many recently discovered ones against large language models (LLMs). However, we discovered that LLMs could reconstruct the altered/removed privacy from given DP-sanitized prompts. We propose two attacks (black-box and white-box) based on the accessibility to LLMs and show that LLMs could connect the pair of DP-sanitized text and the corresponding private training data of LLMs by giving sample text pairs as instructions (in the black-box attacks) or fine-tuning data (in the white-box attacks). To illustrate our findings, we conduct comprehensive experiments on modern LLMs (e.g., LLaMA-2, LLaMA-3, ChatGPT-3.5, ChatGPT-4, ChatGPT-4o, Claude-3, Claude-3.5, OPT, GPT-Neo, GPT-J, Gemma-2, and Pythia) using commonly used datasets (such as WikiMIA, Pile-CC, and Pile-Wiki) against both word-level and sentence-level DP. The experimental results show promising recovery rates, e.g., the black-box attacks against the word-level DP over WikiMIA dataset gave 72.18% on LLaMA-2 (70B), 82.39% on LLaMA-3 (70B), 75.35% on Gemma-2, 91.2% on ChatGPT-4o, and 94.01% on Claude-3.5 (Sonnet). More urgently, this study indicates that these well-known LLMs have emerged as a new security risk for existing DP text sanitization approaches in the current environment.

Weifei Jin, Yuxin Cao, Junjie Su et al.

The widespread application of automatic speech recognition (ASR) supports large-scale voice surveillance, raising concerns about privacy among users. In this paper, we concentrate on using adversarial examples to mitigate unauthorized disclosure of speech privacy thwarted by potential eavesdroppers in speech communications. While audio adversarial examples have demonstrated the capability to mislead ASR models or evade ASR surveillance, they are typically constructed through time-intensive offline optimization, restricting their practicality in real-time voice communication. Recent work overcame this limitation by generating universal adversarial perturbations (UAPs) and enhancing their transferability for black-box scenarios. However, they introduced excessive noise that significantly degrades audio quality and affects human perception, thereby limiting their effectiveness in practical scenarios. To address this limitation and protect live users' speech against ASR systems, we propose a novel framework, AudioShield. Central to this framework is the concept of Transferable Universal Adversarial Perturbations in the Latent Space (LS-TUAP). By transferring the perturbations to the latent space, the audio quality is preserved to a large extent. Additionally, we propose target feature adaptation to enhance the transferability of UAPs by embedding target text features into the perturbations. Comprehensive evaluation on four commercial ASR APIs (Google, Amazon, iFlytek, and Alibaba), three voice assistants, two LLM-powered ASR and one NN-based ASR demonstrates the protection superiority of AudioShield over existing competitors, and both objective and subjective evaluations indicate that AudioShield significantly improves the audio quality. Moreover, AudioShield also shows high effectiveness in real-time end-to-end scenarios, and demonstrates strong resilience against adaptive countermeasures.

Zihan Wang, Zhongkui Ma, Xinguo Feng et al.

Large-scale models are typically adapted to meet the diverse requirements of model owners and users. However, maintaining multiple specialized versions of the model is inefficient. In response, we propose AIM, a novel model modulation paradigm that enables a single model to exhibit diverse behaviors to meet the specific end requirements. AIM enables two key modulation modes: utility and focus modulations. The former provides model owners with dynamic control over output quality to deliver varying utility levels, and the latter offers users precise control to shift model's focused input features. AIM introduces a logits redistribution strategy that operates in a training data-agnostic and retraining-free manner. We establish a formal foundation to ensure AIM's regulation capability, based on the statistical properties of logits ordering via joint probability distributions. Our evaluation confirms AIM's practicality and versatility for Al model modulation, with tasks spanning image classification, semantic segmentation and text generation, and prevalent architectures including ResNet, SegFormer and Llama.

Yansong Gao, Huaibing Peng, Hua Ma et al.

For the first time, we unveil discernible temporal (or historical) trajectory imprints resulting from adversarial example (AE) attacks. Standing in contrast to existing studies all focusing on spatial (or static) imprints within the targeted underlying victim models, we present a fresh temporal paradigm for understanding these attacks. Of paramount discovery is that these imprints are encapsulated within a single loss metric, spanning universally across diverse tasks such as classification and regression, and modalities including image, text, and audio. Recognizing the distinct nature of loss between adversarial and clean examples, we exploit this temporal imprint for AE detection by proposing TRAIT (TRaceable Adversarial temporal trajectory ImprinTs). TRAIT operates under minimal assumptions without prior knowledge of attacks, thereby framing the detection challenge as a one-class classification problem. However, detecting AEs is still challenged by significant overlaps between the constructed synthetic losses of adversarial and clean examples due to the absence of ground truth for incoming inputs. TRAIT addresses this challenge by converting the synthetic loss into a spectrum signature, using the technique of Fast Fourier Transform to highlight the discrepancies, drawing inspiration from the temporal nature of the imprints, analogous to time-series signals. Across 12 AE attacks including SMACK (USENIX Sec'2023), TRAIT demonstrates consistent outstanding performance across comprehensively evaluated modalities, tasks, datasets, and model architectures. In all scenarios, TRAIT achieves an AE detection accuracy exceeding 97%, often around 99%, while maintaining a false rejection rate of 1%. TRAIT remains effective under the formulated strong adaptive attacks.

Minh Trung Tran, Nasrin Sohrabi, Zahir Tari et al.

We identify the slow liquidity drain (SLID) scam, an insidious and highly profitable threat to decentralized finance (DeFi), posing a large-scale, persistent, and growing risk to the ecosystem. Unlike traditional scams such as rug pulls or honeypots (USENIX Sec'19, USENIX Sec'23), SLID gradually siphons funds from liquidity pools over extended periods, making detection significantly more challenging. In this paper, we conducted the first large-scale empirical analysis of 319,166 liquidity pools across six major decentralized exchanges (DEXs) since 2018. We identified 3,117 SLID affected liquidity pools, resulting in cumulative losses of more than US$103 million. We propose a rule-based heuristic and an enhanced machine learning model for early detection. Our machine learning model achieves a detection speed 4.77 times faster than the heuristic while maintaining 95% accuracy. Our study establishes a foundation for protecting DeFi investors at an early stage and promoting transparency in the DeFi ecosystem.

Yuxin Cao, Jinghao Li, Xi Xiao et al.

Previous work has shown that well-crafted adversarial perturbations can threaten the security of video recognition systems. Attackers can invade such models with a low query budget when the perturbations are semantic-invariant, such as StyleFool. Despite the query efficiency, the naturalness of the minutia areas still requires amelioration, since StyleFool leverages style transfer to all pixels in each frame. To close the gap, we propose LocalStyleFool, an improved black-box video adversarial attack that superimposes regional style-transfer-based perturbations on videos. Benefiting from the popularity and scalably usability of Segment Anything Model (SAM), we first extract different regions according to semantic information and then track them through the video stream to maintain the temporal consistency. Then, we add style-transfer-based perturbations to several regions selected based on the associative criterion of transfer-based gradient information and regional area. Perturbation fine adjustment is followed to make stylized videos adversarial. We demonstrate that LocalStyleFool can improve both intra-frame and inter-frame naturalness through a human-assessed survey, while maintaining competitive fooling rate and query efficiency. Successful experiments on the high-resolution dataset also showcase that scrupulous segmentation of SAM helps to improve the scalability of adversarial attacks under high-resolution data.

Longkun Guo, Chaoqi Jia, Kewen Liao et al.

Center-based clustering has attracted significant research interest from both theory and practice. In many practical applications, input data often contain background knowledge that can be used to improve clustering results. In this work, we build on widely adopted $k$-center clustering and model its input background knowledge as must-link (ML) and cannot-link (CL) constraint sets. However, most clustering problems including $k$-center are inherently $\mathcal{NP}$-hard, while the more complex constrained variants are known to suffer severer approximation and computation barriers that significantly limit their applicability. By employing a suite of techniques including reverse dominating sets, linear programming (LP) integral polyhedron, and LP duality, we arrive at the first efficient approximation algorithm for constrained $k$-center with the best possible ratio of 2. We also construct competitive baseline algorithms and empirically evaluate our approximation algorithm against them on a variety of real datasets. The results validate our theoretical findings and demonstrate the great advantages of our algorithm in terms of clustering cost, clustering quality, and running time.

Hua Ma, Ruoxi Sun, Minhui Xue et al.

Accurate time-series forecasting is increasingly critical for planning and operations in low-carbon power systems. Emerging time-series large language models (TS-LLMs) now deliver this capability at scale, requiring no task-specific retraining, and are quickly becoming essential components within the Internet-of-Energy (IoE) ecosystem. However, their real-world deployment is complicated by a critical vulnerability: adversarial examples (AEs). Detecting these AEs is challenging because (i) adversarial perturbations are optimized across the entire input sequence and exploit global temporal dependencies, which renders local detection methods ineffective, and (ii) unlike traditional forecasting models with fixed input dimensions, TS-LLMs accept sequences of variable length, increasing variability that complicates detection. To address these challenges, we propose a plug-in detection framework that capitalizes on the TS-LLM's own variable-length input capability. Our method uses sampling-induced divergence as a detection signal. Given an input sequence, we generate multiple shortened variants and detect AEs by measuring the consistency of their forecasts: Benign sequences tend to produce stable predictions under sampling, whereas adversarial sequences show low forecast similarity, because perturbations optimized for a full-length sequence do not transfer reliably to shorter, differently-structured subsamples. We evaluate our approach on three representative TS-LLMs (TimeGPT, TimesFM, and TimeLLM) across three energy datasets: ETTh2 (Electricity Transformer Temperature), NI (Hourly Energy Consumption), and Consumption (Hourly Electricity Consumption and Production). Empirical results confirm strong and robust detection performance across both black-box and white-box attack scenarios, highlighting its practicality as a reliable safeguard for TS-LLM forecasting in real-world energy systems.

Zihan Wang, Zhongkui Ma, Xinguo Feng et al.

Deep neural networks (DNNs) have become valuable intellectual property of model owners, due to the substantial resources required for their development. To protect these assets in the deployed environment, recent research has proposed model usage control mechanisms to ensure models cannot be used without proper authorization. These methods typically lock the utility of the model by embedding an access key into its parameters. However, they often assume static deployment, and largely fail to withstand continual post-deployment model updates, such as fine-tuning or task-specific adaptation. In this paper, we propose ADALOC, to endow key-based model usage control with adaptability during model evolution. It strategically selects a subset of weights as an intrinsic access key, which enables all model updates to be confined to this key throughout the evolution lifecycle. ADALOC enables using the access key to restore the keyed model to the latest authorized states without redistributing the entire network (i.e., adaptation), and frees the model owner from full re-keying after each model update (i.e., lock preservation). We establish a formal foundation to underpin ADALOC, providing crucial bounds such as the errors introduced by updates restricted to the access key. Experiments on standard benchmarks, such as CIFAR-100, Caltech-256, and Flowers-102, and modern architectures, including ResNet, DenseNet, and ConvNeXt, demonstrate that ADALOC achieves high accuracy under significant updates while retaining robust protections. Specifically, authorized usages consistently achieve strong task-specific performance, while unauthorized usage accuracy drops to near-random guessing levels (e.g., 1.01% on CIFAR-100), compared to up to 87.01% without ADALOC. This shows that ADALOC can offer a practical solution for adaptive and protected DNN deployment in evolving real-world scenarios.

Zihan Wang, Zhiyong Ma, Zhongkui Ma et al.

Recent AI regulations call for data that remain useful for innovation while resistant to misuse, balancing utility with protection at the model level. Existing approaches either perturb data to make it unlearnable or retrain models to suppress transfer, but neither governs inference by unknown models, and both typically require control over training. We propose non-transferable examples (NEs), a training-free and data-agnostic input-side usage-control mechanism. We recode inputs within a model-specific low-sensitivity subspace, preserving outputs for the authorized model while reducing performance on unauthorized models through subspace misalignment. We establish formal bounds that guarantee utility for the authorized model and quantify deviation for unauthorized ones, with the Hoffman-Wielandt inequality linking degradation to spectral differences. Empirically, NEs retain performance on diverse vision backbones and state-of-the-art vision-language models under common preprocessing, whereas non-target models collapse even with reconstruction attempts. These results establish NEs as a practical means to preserve intended data utility while preventing unauthorized exploitation. Our project is available at https://trusted-system-lab.github.io/model-specificity

Jiamin Chang, Haoyang Li, Hammond Pearce et al.

The growing adoption of artificial intelligence (AI) has amplified concerns about trustworthiness, including integrity, privacy, robustness, and bias. To assess and attribute these threats, we propose ConceptLens, a generic framework that leverages pre-trained multimodal models to identify the root causes of integrity threats by analyzing Concept Shift in probing samples. ConceptLens demonstrates strong detection performance for vanilla data poisoning attacks and uncovers vulnerabilities to bias injection, such as the generation of covert advertisements through malicious concept shifts. It identifies privacy risks in unaltered but high-risk samples, filters them before training, and provides insights into model weaknesses arising from incomplete or imbalanced training data. Additionally, at the model level, it attributes concepts that the target model is overly dependent on, identifies misleading concepts, and explains how disrupting key concepts negatively impacts the model. Furthermore, it uncovers sociological biases in generative content, revealing disparities across sociological contexts. Strikingly, ConceptLens reveals how safe training and inference data can be unintentionally and easily exploited, potentially undermining safety alignment. Our study informs actionable insights to breed trust in AI systems, thereby speeding adoption and driving greater innovation.

Zhiyu Zhu, Zhibo Jin, Hongsheng Hu et al.

AI systems, in particular with deep learning techniques, have demonstrated superior performance for various real-world applications. Given the need for tailored optimization in specific scenarios, as well as the concerns related to the exploits of subsurface vulnerabilities, a more comprehensive and in-depth testing AI system becomes a pivotal topic. We have seen the emergence of testing tools in real-world applications that aim to expand testing capabilities. However, they often concentrate on ad-hoc tasks, rendering them unsuitable for simultaneously testing multiple aspects or components. Furthermore, trustworthiness issues arising from adversarial attacks and the challenge of interpreting deep learning models pose new challenges for developing more comprehensive and in-depth AI system testing tools. In this study, we design and implement a testing tool, \tool, to comprehensively and effectively evaluate AI systems. The tool extensively assesses multiple measurements towards adversarial robustness, model interpretability, and performs neuron analysis. The feasibility of the proposed testing tool is thoroughly validated across various modalities, including image classification, object detection, and text classification. Extensive experiments demonstrate that \tool is the state-of-the-art tool for a comprehensive assessment of the robustness and trustworthiness of AI systems. Our research sheds light on a general solution for AI systems testing landscape.

Derui Wang, Minhui Xue, Bo Li et al.

The exploitation of publicly accessible data has led to escalating concerns regarding data privacy and intellectual property (IP) breaches in the age of artificial intelligence. To safeguard both data privacy and IP-related domain knowledge, efforts have been undertaken to render shared data unlearnable for unauthorized models in the wild. Existing methods apply empirically optimized perturbations to the data in the hope of disrupting the correlation between the inputs and the corresponding labels such that the data samples are converted into Unlearnable Examples (UEs). Nevertheless, the absence of mechanisms to verify the robustness of UEs against uncertainty in unauthorized models and their training procedures engenders several under-explored challenges. First, it is hard to quantify the unlearnability of UEs against unauthorized adversaries from different runs of training, leaving the soundness of the defense in obscurity. Particularly, as a prevailing evaluation metric, empirical test accuracy faces generalization errors and may not plausibly represent the quality of UEs. This also leaves room for attackers, as there is no rigid guarantee of the maximal test accuracy achievable by attackers. Furthermore, we find that a simple recovery attack can restore the clean-task performance of the classifiers trained on UEs by slightly perturbing the learned weights. To mitigate the aforementioned problems, in this paper, we propose a mechanism for certifying the so-called $(q, η)$-Learnability of an unlearnable dataset via parametric smoothing. A lower certified $(q, η)$-Learnability indicates a more robust and effective protection over the dataset. Concretely, we 1) improve the tightness of certified $(q, η)$-Learnability and 2) design Provably Unlearnable Examples (PUEs) which have reduced $(q, η)$-Learnability.

Aoting Hu, Zhigang Lu, Renjie Xie et al.

Deploying Machine Learning as a Service gives rise to model plagiarism, leading to copyright infringement. Ownership testing techniques are designed to identify model fingerprints for verifying plagiarism. However, previous works often rely on overfitting or robustness features as fingerprints, lacking theoretical guarantees and exhibiting under-performance on generalized models. In this paper, we propose a novel ownership testing method called VeriDIP, which verifies a DNN model's intellectual property. VeriDIP makes two major contributions. (1) It utilizes membership inference attacks to estimate the lower bound of privacy leakage, which reflects the fingerprint of a given model. The privacy leakage fingerprints highlight the unique patterns through which the models memorize sensitive training datasets. (2) We introduce a novel approach using less private samples to enhance the performance of ownership testing. Extensive experimental results confirm that VeriDIP is effective and efficient in validating the ownership of deep learning models trained on both image and tabular datasets. VeriDIP achieves comparable performance to state-of-the-art methods on image datasets while significantly reducing computation and communication costs. Enhanced VeriDIP demonstrates superior verification performance on generalized deep learning models, particularly on table-trained models. Additionally, VeriDIP exhibits similar effectiveness on utility-preserving differentially private models compared to non-differentially private baselines.

Yuxin Cao, Xi Xiao, Ruoxi Sun et al.

Video classification systems are vulnerable to adversarial attacks, which can create severe security problems in video verification. Current black-box attacks need a large number of queries to succeed, resulting in high computational overhead in the process of attack. On the other hand, attacks with restricted perturbations are ineffective against defenses such as denoising or adversarial training. In this paper, we focus on unrestricted perturbations and propose StyleFool, a black-box video adversarial attack via style transfer to fool the video classification system. StyleFool first utilizes color theme proximity to select the best style image, which helps avoid unnatural details in the stylized videos. Meanwhile, the target class confidence is additionally considered in targeted attacks to influence the output distribution of the classifier by moving the stylized video closer to or even across the decision boundary. A gradient-free method is then employed to further optimize the adversarial perturbations. We carry out extensive experiments to evaluate StyleFool on two standard datasets, UCF-101 and HMDB-51. The experimental results demonstrate that StyleFool outperforms the state-of-the-art adversarial attacks in terms of both the number of queries and the robustness against existing defenses. Moreover, 50% of the stylized videos in untargeted attacks do not need any query since they can already fool the video classification model. Furthermore, we evaluate the indistinguishability through a user study to show that the adversarial samples of StyleFool look imperceptible to human eyes, despite unrestricted perturbations.

Zirui Peng, Shaofeng Li, Guoxing Chen et al.

In this paper, we propose a novel and practical mechanism which enables the service provider to verify whether a suspect model is stolen from the victim model via model extraction attacks. Our key insight is that the profile of a DNN model's decision boundary can be uniquely characterized by its Universal Adversarial Perturbations (UAPs). UAPs belong to a low-dimensional subspace and piracy models' subspaces are more consistent with victim model's subspace compared with non-piracy model. Based on this, we propose a UAP fingerprinting method for DNN models and train an encoder via contrastive learning that takes fingerprint as inputs, outputs a similarity score. Extensive studies show that our framework can detect model IP breaches with confidence > 99.99 within only 20 fingerprints of the suspect model. It has good generalizability across different model architectures and is robust against post-modifications on stolen models.

Chunyi Zhou, Yansong Gao, Anmin Fu et al.

Federated learning (FL) trains a global model across a number of decentralized users, each with a local dataset. Compared to traditional centralized learning, FL does not require direct access to local datasets and thus aims to mitigate data privacy concerns. However, data privacy leakage in FL still exists due to inference attacks, including membership inference, property inference, and data inversion. In this work, we propose a new type of privacy inference attack, coined Preference Profiling Attack (PPA), that accurately profiles the private preferences of a local user, e.g., most liked (disliked) items from the client's online shopping and most common expressions from the user's selfies. In general, PPA can profile top-k (i.e., k = 1, 2, 3 and k = 1 in particular) preferences contingent on the local client (user)'s characteristics. Our key insight is that the gradient variation of a local user's model has a distinguishable sensitivity to the sample proportion of a given class, especially the majority (minority) class. By observing a user model's gradient sensitivity to a class, PPA can profile the sample proportion of the class in the user's local dataset, and thus the user's preference of the class is exposed. The inherent statistical heterogeneity of FL further facilitates PPA. We have extensively evaluated the PPA's effectiveness using four datasets (MNIST, CIFAR10, RAF-DB and Products-10K). Our results show that PPA achieves 90% and 98% top-1 attack accuracy to the MNIST and CIFAR10, respectively. More importantly, in real-world commercial scenarios of shopping (i.e., Products-10K) and social network (i.e., RAF-DB), PPA gains a top-1 attack accuracy of 78% in the former case to infer the most ordered items (i.e., as a commercial competitor), and 88% in the latter case to infer a victim user's most often facial expressions, e.g., disgusted.

Kunpeng Zhang, Xi Xiao, Xiaogang Zhu et al.

Coverage-guided Greybox Fuzzing (CGF) is one of the most successful and widely-used techniques for bug hunting. Two major approaches are adopted to optimize CGF: (i) to reduce search space of inputs by inferring relationships between input bytes and path constraints; (ii) to formulate fuzzing processes (e.g., path transitions) and build up probability distributions to optimize power schedules, i.e., the number of inputs generated per seed. However, the former is subjective to the inference results which may include extra bytes for a path constraint, thereby limiting the efficiency of path constraints resolution, code coverage discovery, and bugs exposure; the latter formalization, concentrating on power schedules for seeds alone, is inattentive to the schedule for bytes in a seed. In this paper, we propose a lightweight fuzzing approach, Truzz, to optimize existing Coverage-guided Greybox Fuzzers (CGFs). To address two aforementioned challenges, Truzz identifies the bytes related to the validation checks (i.e., the checks guarding error-handling code), and protects those bytes from being frequently mutated, making most generated inputs examine the functionalities of programs, in lieu of being rejected by validation checks. The byte-wise relationship determination mitigates the problem of loading extra bytes when fuzzers infer the byte-constraint relation. Furthermore, the proposed path transition within Truzz can efficiently prioritize the seed as the new path, harvesting many new edges, and the new path likely belongs to a code region with many undiscovered code lines. The experimental results show that on average, Truzz can generate 16.14% more inputs flowing into functional code, in addition to 24.75% more new edges than the vanilla fuzzers. Finally, our approach exposes 13 bugs in 8 target programs, and 6 of them have not been identified by the vanilla fuzzers.

Matthew Crawford, Wei Wang, Ruoxi Sun et al.

With the rapid growth of malware attacks, more antivirus developers consider deploying machine learning technologies into their productions. Researchers and developers published various machine learning-based detectors with high precision on malware detection in recent years. Although numerous machine learning-based malware detectors are available, they face various machine learning-targeted attacks, including evasion and adversarial attacks. This project explores how and why adversarial examples evade malware detectors, then proposes a randomised chaining method to defend against adversarial malware statically. This research is crucial for working towards combating the pertinent malware cybercrime.

Hamish Spencer, Wei Wang, Ruoxi Sun et al.

With the increasingly rapid development of new malicious computer software by bad faith actors, both commercial and research-oriented antivirus detectors have come to make greater use of machine learning tactics to identify such malware as harmful before end users are exposed to their effects. This, in turn, has spurred the development of tools that allow for known malware to be manipulated such that they can evade being classified as dangerous by these machine learning-based detectors, while retaining their malicious functionality. These manipulations function by applying a set of changes that can be made to Windows programs that result in a different file structure and signature without altering the software's capabilities. Various proposals have been made for the most effective way of applying these alterations to input malware to deceive static malware detectors; the purpose of this research is to examine these proposals and test their implementations to determine which tactics tend to generate the most successful attacks.

Bao Gia Doan, Minhui Xue, Shiqing Ma et al.

Deep neural networks are vulnerable to attacks from adversarial inputs and, more recently, Trojans to misguide or hijack the model's decision. We expose the existence of an intriguing class of spatially bounded, physically realizable, adversarial examples -- Universal NaTuralistic adversarial paTches -- we call TnTs, by exploring the superset of the spatially bounded adversarial example space and the natural input space within generative adversarial networks. Now, an adversary can arm themselves with a patch that is naturalistic, less malicious-looking, physically realizable, highly effective achieving high attack success rates, and universal. A TnT is universal because any input image captured with a TnT in the scene will: i) misguide a network (untargeted attack); or ii) force the network to make a malicious decision (targeted attack). Interestingly, now, an adversarial patch attacker has the potential to exert a greater level of control -- the ability to choose a location-independent, natural-looking patch as a trigger in contrast to being constrained to noisy perturbations -- an ability is thus far shown to be only possible with Trojan attack methods needing to interfere with the model building processes to embed a backdoor at the risk discovery; but, still realize a patch deployable in the physical world. Through extensive experiments on the large-scale visual classification task, ImageNet with evaluations across its entire validation set of 50,000 images, we demonstrate the realistic threat from TnTs and the robustness of the attack. We show a generalization of the attack to create patches achieving higher attack success rates than existing state-of-the-art methods. Our results show the generalizability of the attack to different visual classification tasks (CIFAR-10, GTSRB, PubFig) and multiple state-of-the-art deep neural networks such as WideResnet50, Inception-V3 and VGG-16.

Hua Ma, Huming Qiu, Yansong Gao et al.

Currently, there is a burgeoning demand for deploying deep learning (DL) models on ubiquitous edge Internet of Things (IoT) devices attributed to their low latency and high privacy preservation. However, DL models are often large in size and require large-scale computation, which prevents them from being placed directly onto IoT devices, where resources are constrained and 32-bit floating-point (float-32) operations are unavailable. Commercial framework (i.e., a set of toolkits) empowered model quantization is a pragmatic solution that enables DL deployment on mobile devices and embedded systems by effortlessly post-quantizing a large high-precision model (e.g., float-32) into a small low-precision model (e.g., int-8) while retaining the model inference accuracy. However, their usability might be threatened by security vulnerabilities. This work reveals that the standard quantization toolkits can be abused to activate a backdoor. We demonstrate that a full-precision backdoored model which does not have any backdoor effect in the presence of a trigger -- as the backdoor is dormant -- can be activated by the default i) TensorFlow-Lite (TFLite) quantization, the only product-ready quantization framework to date, and ii) the beta released PyTorch Mobile framework. When each of the float-32 models is converted into an int-8 format model through the standard TFLite or Pytorch Mobile framework's post-training quantization, the backdoor is activated in the quantized model, which shows a stable attack success rate close to 100% upon inputs with the trigger, while it behaves normally upon non-trigger inputs. This work highlights that a stealthy security threat occurs when an end user utilizes the on-device post-training model quantization frameworks, informing security researchers of cross-platform overhaul of DL models post quantization even if these models pass front-end backdoor inspections.

Aoting Hu, Renjie Xie, Zhigang Lu et al.

Generative Adversarial Networks (GAN)-synthesized table publishing lets people privately learn insights without access to the private table. However, existing studies on Membership Inference (MI) Attacks show promising results on disclosing membership of training datasets of GAN-synthesized tables. Different from those works focusing on discovering membership of a given data point, in this paper, we propose a novel Membership Collision Attack against GANs (TableGAN-MCA), which allows an adversary given only synthetic entries randomly sampled from a black-box generator to recover partial GAN training data. Namely, a GAN-synthesized table immune to state-of-the-art MI attacks is vulnerable to the TableGAN-MCA. The success of TableGAN-MCA is boosted by an observation that GAN-synthesized tables potentially collide with the training data of the generator. Our experimental evaluations on TableGAN-MCA have five main findings. First, TableGAN-MCA has a satisfying training data recovery rate on three commonly used real-world datasets against four generative models. Second, factors, including the size of GAN training data, GAN training epochs and the number of synthetic samples available to the adversary, are positively correlated to the success of TableGAN-MCA. Third, highly frequent data points have high risks of being recovered by TableGAN-MCA. Fourth, some unique data are exposed to unexpected high recovery risks in TableGAN-MCA, which may attribute to GAN's generalization. Fifth, as expected, differential privacy, without the consideration of the correlations between features, does not show commendable mitigation effect against the TableGAN-MCA. Finally, we propose two mitigation methods and show promising privacy and utility trade-offs when protecting against TableGAN-MCA.

Zihan Wang, Olivia Byrnes, Hu Wang et al.

The advancement of secure communication and identity verification fields has significantly increased through the use of deep learning techniques for data hiding. By embedding information into a noise-tolerant signal such as audio, video, or images, digital watermarking and steganography techniques can be used to protect sensitive intellectual property and enable confidential communication, ensuring that the information embedded is only accessible to authorized parties. This survey provides an overview of recent developments in deep learning techniques deployed for data hiding, categorized systematically according to model architectures and noise injection methods. The objective functions, evaluation metrics, and datasets used for training these data hiding models are comprehensively summarised. Additionally, potential future research directions that unite digital watermarking and steganography on software engineering to enhance security and mitigate risks are suggested and deliberated. This contribution furthers the creation of a more trustworthy digital world and advances Responsible AI.