Shouling Ji

Yangkai Du, Tengfei Ma, Lingfei Wu et al. · stanford

Towards real-world information extraction scenario, research of relation extraction is advancing to document-level relation extraction(DocRE). Existing approaches for DocRE aim to extract relation by encoding various information sources in the long context by novel model architectures. However, the inherent long-tailed distribution problem of DocRE is overlooked by prior work. We argue that mitigating the long-tailed distribution problem is crucial for DocRE in the real-world scenario. Motivated by the long-tailed distribution problem, we propose an Easy Relation Augmentation(ERA) method for improving DocRE by enhancing the performance of tailed relations. In addition, we further propose a novel contrastive learning framework based on our ERA, i.e., ERACL, which can further improve the model performance on tailed relations and achieve competitive overall DocRE performance compared to the state-of-arts.

Jinyin Chen, Haibin Zheng, Tao Liu et al.

With the development of deep learning processors and accelerators, deep learning models have been widely deployed on edge devices as part of the Internet of Things. Edge device models are generally considered as valuable intellectual properties that are worth for careful protection. Unfortunately, these models have a great risk of being stolen or illegally copied. The existing model protections using encryption algorithms are suffered from high computation overhead which is not practical due to the limited computing capacity on edge devices. In this work, we propose a light-weight, practical, and general Edge device model Pro tection method at neuron level, denoted as EdgePro. Specifically, we select several neurons as authorization neurons and set their activation values to locking values and scale the neuron outputs as the "asswords" during training. EdgePro protects the model by ensuring it can only work correctly when the "passwords" are met, at the cost of encrypting and storing the information of the "passwords" instead of the whole model. Extensive experimental results indicate that EdgePro can work well on the task of protecting on datasets with different modes. The inference time increase of EdgePro is only 60% of state-of-the-art methods, and the accuracy loss is less than 1%. Additionally, EdgePro is robust against adaptive attacks including fine-tuning and pruning, which makes it more practical in real-world applications. EdgePro is also open sourced to facilitate future research: https://github.com/Leon022/Edg

Xiangshan Gao, Xingjun Ma, Jingyi Wang et al.

Federated learning (FL) is a collaborative learning paradigm where participants jointly train a powerful model without sharing their private data. One desirable property for FL is the implementation of the right to be forgotten (RTBF), i.e., a leaving participant has the right to request to delete its private data from the global model. However, unlearning itself may not be enough to implement RTBF unless the unlearning effect can be independently verified, an important aspect that has been overlooked in the current literature. In this paper, we prompt the concept of verifiable federated unlearning, and propose VeriFi, a unified framework integrating federated unlearning and verification that allows systematic analysis of the unlearning and quantification of its effect, with different combinations of multiple unlearning and verification methods. In VeriFi, the leaving participant is granted the right to verify (RTV), that is, the participant notifies the server before leaving, then actively verifies the unlearning effect in the next few communication rounds. The unlearning is done at the server side immediately after receiving the leaving notification, while the verification is done locally by the leaving participant via two steps: marking (injecting carefully-designed markers to fingerprint the leaver) and checking (examining the change of the global model's performance on the markers). Based on VeriFi, we conduct the first systematic and large-scale study for verifiable federated unlearning, considering 7 unlearning methods and 5 verification methods. Particularly, we propose a more efficient and FL-friendly unlearning method, and two more effective and robust non-invasive-verification methods. We extensively evaluate VeriFi on 7 datasets and 4 types of deep learning models. Our analysis establishes important empirical understandings for more trustworthy federated unlearning.

Zhaohan Xi, Tianyu Du, Changjiang Li et al.

Pre-trained language models (PLMs) have demonstrated remarkable performance as few-shot learners. However, their security risks under such settings are largely unexplored. In this work, we conduct a pilot study showing that PLMs as few-shot learners are highly vulnerable to backdoor attacks while existing defenses are inadequate due to the unique challenges of few-shot scenarios. To address such challenges, we advocate MDP, a novel lightweight, pluggable, and effective defense for PLMs as few-shot learners. Specifically, MDP leverages the gap between the masking-sensitivity of poisoned and clean samples: with reference to the limited few-shot data as distributional anchors, it compares the representations of given samples under varying masking and identifies poisoned samples as ones with significant variations. We show analytically that MDP creates an interesting dilemma for the attacker to choose between attack effectiveness and detection evasiveness. The empirical evaluation using benchmark datasets and representative attacks validates the efficacy of MDP.

Changjiang Li, Ren Pang, Zhaohan Xi et al.

As a new paradigm in machine learning, self-supervised learning (SSL) is capable of learning high-quality representations of complex data without relying on labels. In addition to eliminating the need for labeled data, research has found that SSL improves the adversarial robustness over supervised learning since lacking labels makes it more challenging for adversaries to manipulate model predictions. However, the extent to which this robustness superiority generalizes to other types of attacks remains an open question. We explore this question in the context of backdoor attacks. Specifically, we design and evaluate CTRL, an embarrassingly simple yet highly effective self-supervised backdoor attack. By only polluting a tiny fraction of training data (<= 1%) with indistinguishable poisoning samples, CTRL causes any trigger-embedded input to be misclassified to the adversary's designated class with a high probability (>= 99%) at inference time. Our findings suggest that SSL and supervised learning are comparably vulnerable to backdoor attacks. More importantly, through the lens of CTRL, we study the inherent vulnerability of SSL to backdoor attacks. With both empirical and analytical evidence, we reveal that the representation invariance property of SSL, which benefits adversarial robustness, may also be the very reason making \ssl highly susceptible to backdoor attacks. Our findings also imply that the existing defenses against supervised backdoor attacks are not easily retrofitted to the unique vulnerability of SSL.

Yuhao Mao, Chong Fu, Saizhuo Wang et al.

One intriguing property of adversarial attacks is their "transferability" -- an adversarial example crafted with respect to one deep neural network (DNN) model is often found effective against other DNNs as well. Intensive research has been conducted on this phenomenon under simplistic controlled conditions. Yet, thus far, there is still a lack of comprehensive understanding about transferability-based attacks ("transfer attacks") in real-world environments. To bridge this critical gap, we conduct the first large-scale systematic empirical study of transfer attacks against major cloud-based MLaaS platforms, taking the components of a real transfer attack into account. The study leads to a number of interesting findings which are inconsistent to the existing ones, including: (1) Simple surrogates do not necessarily improve real transfer attacks. (2) No dominant surrogate architecture is found in real transfer attacks. (3) It is the gap between posterior (output of the softmax layer) rather than the gap between logit (so-called $κ$ value) that increases transferability. Moreover, by comparing with prior works, we demonstrate that transfer attacks possess many previously unknown properties in real-world environments, such as (1) Model similarity is not a well-defined concept. (2) $L_2$ norm of perturbation can generate high transferability without usage of gradient and is a more powerful source than $L_\infty$ norm. We believe this work sheds light on the vulnerabilities of popular MLaaS platforms and points to a few promising research directions.

Pengyu Qiu, Xuhong Zhang, Shouling Ji et al.

Vertical Federated Learning (VFL) is a trending collaborative machine learning model training solution. Existing industrial frameworks employ secure multi-party computation techniques such as homomorphic encryption to ensure data security and privacy. Despite these efforts, studies have revealed that data leakage remains a risk in VFL due to the correlations between intermediate representations and raw data. Neural networks can accurately capture these correlations, allowing an adversary to reconstruct the data. This emphasizes the need for continued research into securing VFL systems. Our work shows that hashing is a promising solution to counter data reconstruction attacks. The one-way nature of hashing makes it difficult for an adversary to recover data from hash codes. However, implementing hashing in VFL presents new challenges, including vanishing gradients and information loss. To address these issues, we propose HashVFL, which integrates hashing and simultaneously achieves learnability, bit balance, and consistency. Experimental results indicate that HashVFL effectively maintains task performance while defending against data reconstruction attacks. It also brings additional benefits in reducing the degree of label leakage, mitigating adversarial attacks, and detecting abnormal inputs. We hope our work will inspire further research into the potential applications of HashVFL.

Chuer Yu, Xuhong Zhang, Yuxuan Duan et al.

Despite the fact that DeepFake forgery detection algorithms have achieved impressive performance on known manipulations, they often face disastrous performance degradation when generalized to an unseen manipulation. Some recent works show improvement in generalization but rely on features fragile to image distortions such as compression. To this end, we propose Diff-ID, a concise and effective approach that explains and measures the identity loss induced by facial manipulations. When testing on an image of a specific person, Diff-ID utilizes an authentic image of that person as a reference and aligns them to the same identity-insensitive attribute feature space by applying a face-swapping generator. We then visualize the identity loss between the test and the reference image from the image differences of the aligned pairs, and design a custom metric to quantify the identity loss. The metric is then proved to be effective in distinguishing the forgery images from the real ones. Extensive experiments show that our approach achieves high detection performance on DeepFake images and state-of-the-art generalization ability to unknown forgery methods, while also being robust to image distortions.

Yuyou Gan, Yuhao Mao, Xuhong Zhang et al.

Understanding the decision process of neural networks is hard. One vital method for explanation is to attribute its decision to pivotal features. Although many algorithms are proposed, most of them solely improve the faithfulness to the model. However, the real environment contains many random noises, which may leads to great fluctuations in the explanations. More seriously, recent works show that explanation algorithms are vulnerable to adversarial attacks. All of these make the explanation hard to trust in real scenarios. To bridge this gap, we propose a model-agnostic method \emph{Median Test for Feature Attribution} (MeTFA) to quantify the uncertainty and increase the stability of explanation algorithms with theoretical guarantees. MeTFA has the following two functions: (1) examine whether one feature is significantly important or unimportant and generate a MeTFA-significant map to visualize the results; (2) compute the confidence interval of a feature attribution score and generate a MeTFA-smoothed map to increase the stability of the explanation. Experiments show that MeTFA improves the visual quality of explanations and significantly reduces the instability while maintaining the faithfulness. To quantitatively evaluate the faithfulness of an explanation under different noise settings, we further propose several robust faithfulness metrics. Experiment results show that the MeTFA-smoothed explanation can significantly increase the robust faithfulness. In addition, we use two scenarios to show MeTFA's potential in the applications. First, when applied to the SOTA explanation method to locate context bias for semantic segmentation models, MeTFA-significant explanations use far smaller regions to maintain 99\%+ faithfulness. Second, when tested with different explanation-oriented attacks, MeTFA can help defend vanilla, as well as adaptive, adversarial attacks against explanations.

Linkang Du, Min Chen, Mingyang Sun et al.

Data is a critical asset in AI, as high-quality datasets can significantly improve the performance of machine learning models. In safety-critical domains such as autonomous vehicles, offline deep reinforcement learning (offline DRL) is frequently used to train models on pre-collected datasets, as opposed to training these models by interacting with the real-world environment as the online DRL. To support the development of these models, many institutions make datasets publicly available with opensource licenses, but these datasets are at risk of potential misuse or infringement. Injecting watermarks to the dataset may protect the intellectual property of the data, but it cannot handle datasets that have already been published and is infeasible to be altered afterward. Other existing solutions, such as dataset inference and membership inference, do not work well in the offline DRL scenario due to the diverse model behavior characteristics and offline setting constraints. In this paper, we advocate a new paradigm by leveraging the fact that cumulative rewards can act as a unique identifier that distinguishes DRL models trained on a specific dataset. To this end, we propose ORL-AUDITOR, which is the first trajectory-level dataset auditing mechanism for offline RL scenarios. Our experiments on multiple offline DRL models and tasks reveal the efficacy of ORL-AUDITOR, with auditing accuracy over 95% and false positive rates less than 2.88%. We also provide valuable insights into the practical implementation of ORL-AUDITOR by studying various parameter settings. Furthermore, we demonstrate the auditing capability of ORL-AUDITOR on open-source datasets from Google and DeepMind, highlighting its effectiveness in auditing published datasets. ORL-AUDITOR is open-sourced at https://github.com/link-zju/ORL-Auditor.

Chong Fu, Xuhong Zhang, Shouling Ji et al.

Trojan attack on deep neural networks, also known as backdoor attack, is a typical threat to artificial intelligence. A trojaned neural network behaves normally with clean inputs. However, if the input contains a particular trigger, the trojaned model will have attacker-chosen abnormal behavior. Although many backdoor detection methods exist, most of them assume that the defender has access to a set of clean validation samples or samples with the trigger, which may not hold in some crucial real-world cases, e.g., the case where the defender is the maintainer of model-sharing platforms. Thus, in this paper, we propose FreeEagle, the first data-free backdoor detection method that can effectively detect complex backdoor attacks on deep neural networks, without relying on the access to any clean samples or samples with the trigger. The evaluation results on diverse datasets and model architectures show that FreeEagle is effective against various complex backdoor attacks, even outperforming some state-of-the-art non-data-free backdoor detection methods.

Lujia Shen, Xuhong Zhang, Shouling Ji et al.

Currently, natural language processing (NLP) models are wildly used in various scenarios. However, NLP models, like all deep models, are vulnerable to adversarially generated text. Numerous works have been working on mitigating the vulnerability from adversarial attacks. Nevertheless, there is no comprehensive defense in existing works where each work targets a specific attack category or suffers from the limitation of computation overhead, irresistible to adaptive attack, etc. In this paper, we exhaustively investigate the adversarial attack algorithms in NLP, and our empirical studies have discovered that the attack algorithms mainly disrupt the importance distribution of words in a text. A well-trained model can distinguish subtle importance distribution differences between clean and adversarial texts. Based on this intuition, we propose TextDefense, a new adversarial example detection framework that utilizes the target model's capability to defend against adversarial attacks while requiring no prior knowledge. TextDefense differs from previous approaches, where it utilizes the target model for detection and thus is attack type agnostic. Our extensive experiments show that TextDefense can be applied to different architectures, datasets, and attack methods and outperforms existing methods. We also discover that the leading factor influencing the performance of TextDefense is the target model's generalizability. By analyzing the property of the target model and the property of the adversarial example, we provide our insights into the adversarial attacks in NLP and the principles of our defense method.

Dayong Ye, Huiqiang Chen, Shuai Zhou et al.

Transfer learning is an important approach that produces pre-trained teacher models which can be used to quickly build specialized student models. However, recent research on transfer learning has found that it is vulnerable to various attacks, e.g., misclassification and backdoor attacks. However, it is still not clear whether transfer learning is vulnerable to model inversion attacks. Launching a model inversion attack against transfer learning scheme is challenging. Not only does the student model hide its structural parameters, but it is also inaccessible to the adversary. Hence, when targeting a student model, both the white-box and black-box versions of existing model inversion attacks fail. White-box attacks fail as they need the target model's parameters. Black-box attacks fail as they depend on making repeated queries of the target model. However, they may not mean that transfer learning models are impervious to model inversion attacks. Hence, with this paper, we initiate research into model inversion attacks against transfer learning schemes with two novel attack methods. Both are black-box attacks, suiting different situations, that do not rely on queries to the target student model. In the first method, the adversary has the data samples that share the same distribution as the training set of the teacher model. In the second method, the adversary does not have any such samples. Experiments show that highly recognizable data records can be recovered with both of these methods. This means that even if a model is an inaccessible black-box, it can still be inverted.

Zhaohan Xi, Ren Pang, Changjiang Li et al.

Recently, knowledge representation learning (KRL) is emerging as the state-of-the-art approach to process queries over knowledge graphs (KGs), wherein KG entities and the query are embedded into a latent space such that entities that answer the query are embedded close to the query. Yet, despite the intensive research on KRL, most existing studies either focus on homogenous KGs or assume KG completion tasks (i.e., inference of missing facts), while answering complex logical queries over KGs with multiple aspects (multi-view KGs) remains an open challenge. To bridge this gap, in this paper, we present ROMA, a novel KRL framework for answering logical queries over multi-view KGs. Compared with the prior work, ROMA departs in major aspects. (i) It models a multi-view KG as a set of overlaying sub-KGs, each corresponding to one view, which subsumes many types of KGs studied in the literature (e.g., temporal KGs). (ii) It supports complex logical queries with varying relation and view constraints (e.g., with complex topology and/or from multiple views); (iii) It scales up to KGs of large sizes (e.g., millions of facts) and fine-granular views (e.g., dozens of views); (iv) It generalizes to query structures and KG views that are unobserved during training. Extensive empirical evaluation on real-world KGs shows that \system significantly outperforms alternative methods.

Yunruo Zhang, Tianyu Du, Shouling Ji et al.

It is well-known that recurrent neural networks (RNNs), although widely used, are vulnerable to adversarial attacks including one-frame attacks and multi-frame attacks. Though a few certified defenses exist to provide guaranteed robustness against one-frame attacks, we prove that defending against multi-frame attacks remains a challenging problem due to their enormous perturbation space. In this paper, we propose the first certified defense against multi-frame attacks for RNNs called RNN-Guard. To address the above challenge, we adopt the perturb-all-frame strategy to construct perturbation spaces consistent with those in multi-frame attacks. However, the perturb-all-frame strategy causes a precision issue in linear relaxations. To address this issue, we introduce a novel abstract domain called InterZono and design tighter relaxations. We prove that InterZono is more precise than Zonotope yet carries the same time complexity. Experimental evaluations across various datasets and model structures show that the certified robust accuracy calculated by RNN-Guard with InterZono is up to 2.18 times higher than that with Zonotope. In addition, we extend RNN-Guard as the first certified training method against multi-frame attacks to directly enhance RNNs' robustness. The results show that the certified robust accuracy of models trained with RNN-Guard against multi-frame attacks is 15.47 to 67.65 percentage points higher than those with other training methods.

Ping He, Yifan Xia, Xuhong Zhang et al.

The widespread adoption of the Android operating system has made malicious Android applications an appealing target for attackers. Machine learning-based (ML-based) Android malware detection (AMD) methods are crucial in addressing this problem; however, their vulnerability to adversarial examples raises concerns. Current attacks against ML-based AMD methods demonstrate remarkable performance but rely on strong assumptions that may not be realistic in real-world scenarios, e.g., the knowledge requirements about feature space, model parameters, and training dataset. To address this limitation, we introduce AdvDroidZero, an efficient query-based attack framework against ML-based AMD methods that operates under the zero knowledge setting. Our extensive evaluation shows that AdvDroidZero is effective against various mainstream ML-based AMD methods, in particular, state-of-the-art such methods and real-world antivirus solutions.

Ren Pang, Changjiang Li, Zhaohan Xi et al.

This paper asks the intriguing question: is it possible to exploit neural architecture search (NAS) as a new attack vector to launch previously improbable attacks? Specifically, we present EVAS, a new attack that leverages NAS to find neural architectures with inherent backdoors and exploits such vulnerability using input-aware triggers. Compared with existing attacks, EVAS demonstrates many interesting properties: (i) it does not require polluting training data or perturbing model parameters; (ii) it is agnostic to downstream fine-tuning or even re-training from scratch; (iii) it naturally evades defenses that rely on inspecting model parameters or training data. With extensive evaluation on benchmark datasets, we show that EVAS features high evasiveness, transferability, and robustness, thereby expanding the adversary's design spectrum. We further characterize the mechanisms underlying EVAS, which are possibly explainable by architecture-level ``shortcuts'' that recognize trigger patterns. This work raises concerns about the current practice of NAS and points to potential directions to develop effective countermeasures.

Naen Xu, Jiayi Sheng, Changjiang Li et al.

Puns are a common form of rhetorical wordplay that exploits polysemy and phonetic similarity to create humor. In multimodal puns, visual and textual elements synergize to ground the literal sense and evoke the figurative meaning simultaneously. Although Vision-Language Models (VLMs) are widely used in multimodal understanding and generation, their ability to understand puns has not been systematically studied due to a scarcity of rigorous benchmarks. To address this, we first propose a multimodal pun generation pipeline. We then introduce MultiPun, a dataset comprising diverse types of puns alongside adversarial non-pun distractors. Our evaluation reveals that most models struggle to distinguish genuine puns from these distractors. Moreover, we propose both prompt-level and model-level strategies to enhance pun comprehension, with an average improvement of 16.5% in F1 scores. Our findings provide valuable insights for developing future VLMs that master the subtleties of human-like humor via cross-modal reasoning.

Peiyu Liu, Junming Liu, Lirong Fu et al.

Recently, ChatGPT has attracted great attention from the code analysis domain. Prior works show that ChatGPT has the capabilities of processing foundational code analysis tasks, such as abstract syntax tree generation, which indicates the potential of using ChatGPT to comprehend code syntax and static behaviors. However, it is unclear whether ChatGPT can complete more complicated real-world vulnerability management tasks, such as the prediction of security relevance and patch correctness, which require an all-encompassing understanding of various aspects, including code syntax, program semantics, and related manual comments. In this paper, we explore ChatGPT's capabilities on 6 tasks involving the complete vulnerability management process with a large-scale dataset containing 70,346 samples. For each task, we compare ChatGPT against SOTA approaches, investigate the impact of different prompts, and explore the difficulties. The results suggest promising potential in leveraging ChatGPT to assist vulnerability management. One notable example is ChatGPT's proficiency in tasks like generating titles for software bug reports. Furthermore, our findings reveal the difficulties encountered by ChatGPT and shed light on promising future directions. For instance, directly providing random demonstration examples in the prompt cannot consistently guarantee good performance in vulnerability management. By contrast, leveraging ChatGPT in a self-heuristic way -- extracting expertise from demonstration examples itself and integrating the extracted expertise in the prompt is a promising research direction. Besides, ChatGPT may misunderstand and misuse the information in the prompt. Consequently, effectively guiding ChatGPT to focus on helpful information rather than the irrelevant content is still an open problem.

Oubo Ma, Ruixiao Lin, Jiahao Chen et al.

As LLMs become increasingly capable, editorial boards and program committees are growing concerned about reviewers who fully outsource peer review to commercial chatbots. This concern stems from prior findings that current chatbots lack the independent critical thinking and depth of reasoning required to assess scientific novelty. One promising direction for mitigating this concern is to embed hidden instructions into manuscripts that disrupt or alter chatbot-generated reviews. However, existing methods remain intuitive and fragile, as they typically rely on homogeneous payloads injected in an inter-stream manner, rendering them susceptible to sanitization or neutralization. In this paper, we identify End-to-End Review Outsourcing as an emerging threat and propose IntraGuard, a black-box, venue-agnostic defense framework grounded in the structural--visual decoupling inherent to the PDF. Designed for committee-side deployment, IntraGuard supports both explicit strategies that trigger refusal or warning signals, and implicit strategies that embed predefined textual markers into the generated review. These strategies can be deployed via any of three intra-stream injection mechanisms, each of which seamlessly embeds heterogeneous defensive text objects within the PDF's underlying structure without altering its visual presentation. Extensive evaluations across 7 real-world commercial chatbot settings and 12 venues spanning diverse disciplines show that IntraGuard achieves a defense success rate of up to 84%, while preserving peer-review invariance for human reviewers. IntraGuard is lightweight and hardware-independent, incurring an average overhead of only one second per manuscript on a commodity personal computer. We further evaluate 11 adaptive attacks spanning manuscript sanitization and instruction interference, and discuss the implications of constructing ensemble defenses.

Rui Zeng, Xi Chen, Yuwen Pu et al.

Backdoors can be injected into NLP models to induce misbehavior when the input text contains a specific feature, known as a trigger, which the attacker secretly selects. Unlike fixed words, phrases, or sentences used in the static text trigger, NLP dynamic backdoor attacks design triggers associated with abstract and latent text features, making them considerably stealthier than traditional static backdoor attacks. However, existing research on NLP backdoor detection primarily focuses on defending against static backdoor attacks, while detecting dynamic backdoors in NLP models remains largely unexplored. This paper presents CLIBE, the first framework to detect dynamic backdoors in Transformer-based NLP models. CLIBE injects a "few-shot perturbation" into the suspect Transformer model by crafting optimized weight perturbation in the attention layers to make the perturbed model classify a limited number of reference samples as a target label. Subsequently, CLIBE leverages the generalization ability of this few-shot perturbation to determine whether the original model contains a dynamic backdoor. Extensive evaluation on three advanced NLP dynamic backdoor attacks, two widely-used Transformer frameworks, and four real-world classification tasks strongly validates the effectiveness of CLIBE. We also demonstrate the robustness of CLIBE against various adaptive attacks. Furthermore, we employ CLIBE to scrutinize 49 popular Transformer models on Hugging Face and discover one exhibiting a high probability of containing a dynamic backdoor. We have contacted Hugging Face and provided detailed evidence of this model's backdoor behavior. Moreover, we extend CLIBE to detect backdoor text generation models modified to exhibit toxic behavior. To the best of our knowledge, CLIBE is the first framework capable of detecting backdoors in text generation models without access to trigger input test samples.

Yuxuan Duan, Xuhong Zhang, Chuer Yu et al.

Recently, face swapping has been developing rapidly and achieved a surprising reality, raising concerns about fake content. As a countermeasure, various detection approaches have been proposed and achieved promising performance. However, most existing detectors struggle to maintain performance on unseen face swapping methods and low-quality images. Apart from the generalization problem, current detection approaches have been shown vulnerable to evasion attacks crafted by detection-aware manipulators. Lack of robustness under adversary scenarios leaves threats for applying face swapping detection in real world. In this paper, we propose a novel face swapping detection approach based on face identification probability distributions, coined as IdP_FSD, to improve the generalization and robustness. IdP_FSD is specially designed for detecting swapped faces whose identities belong to a finite set, which is meaningful in real-world applications. Compared with previous general detection methods, we make use of the available real faces with concerned identities and require no fake samples for training. IdP_FSD exploits face swapping's common nature that the identity of swapped face combines that of two faces involved in swapping. We reflect this nature with the confusion of a face identification model and measure the confusion with the maximum value of the output probability distribution. What's more, to defend our detector under adversary scenarios, an attention-based finetuning scheme is proposed for the face identification models used in IdP_FSD. Extensive experiments show that the proposed IdP_FSD not only achieves high detection performance on different benchmark datasets and image qualities but also raises the bar for manipulators to evade the detection.

Tong Ye, Lingfei Wu, Tengfei Ma et al.

Automatically generating function summaries for binaries is an extremely valuable but challenging task, since it involves translating the execution behavior and semantics of the low-level language (assembly code) into human-readable natural language. However, most current works on understanding assembly code are oriented towards generating function names, which involve numerous abbreviations that make them still confusing. To bridge this gap, we focus on generating complete summaries for binary functions, especially for stripped binary (no symbol table and debug information in reality). To fully exploit the semantics of assembly code, we present a control flow graph and pseudo code guided binary code summarization framework called CP-BCS. CP-BCS utilizes a bidirectional instruction-level control flow graph and pseudo code that incorporates expert knowledge to learn the comprehensive binary function execution behavior and logic semantics. We evaluate CP-BCS on 3 different binary optimization levels (O1, O2, and O3) for 3 different computer architectures (X86, X64, and ARM). The evaluation results demonstrate CP-BCS is superior and significantly improves the efficiency of reverse engineering.

Lujia Shen, Yuwen Pu, Shouling Ji et al.

Transformer-based models, such as BERT and GPT, have been widely adopted in natural language processing (NLP) due to their exceptional performance. However, recent studies show their vulnerability to textual adversarial attacks where the model's output can be misled by intentionally manipulating the text inputs. Despite various methods that have been proposed to enhance the model's robustness and mitigate this vulnerability, many require heavy consumption resources (e.g., adversarial training) or only provide limited protection (e.g., defensive dropout). In this paper, we propose a novel method called dynamic attention, tailored for the transformer architecture, to enhance the inherent robustness of the model itself against various adversarial attacks. Our method requires no downstream task knowledge and does not incur additional costs. The proposed dynamic attention consists of two modules: (I) attention rectification, which masks or weakens the attention value of the chosen tokens, and (ii) dynamic modeling, which dynamically builds the set of candidate tokens. Extensive experiments demonstrate that dynamic attention significantly mitigates the impact of adversarial attacks, improving up to 33\% better performance than previous methods against widely-used adversarial attacks. The model-level design of dynamic attention enables it to be easily combined with other defense methods (e.g., adversarial training) to further enhance the model's robustness. Furthermore, we demonstrate that dynamic attention preserves the state-of-the-art robustness space of the original model compared to other dynamic modeling methods.

Pengyu Qiu, Xuhong Zhang, Shouling Ji et al.

Vertical federated learning (VFL) is an emerging paradigm that enables collaborators to build machine learning models together in a distributed fashion. In general, these parties have a group of users in common but own different features. Existing VFL frameworks use cryptographic techniques to provide data privacy and security guarantees, leading to a line of works studying computing efficiency and fast implementation. However, the security of VFL's model remains underexplored.

Songze Li, Chuokun Xu, Jiaying Wang et al.

Large Language Models (LLMs) have demonstrated exceptional capabilities across diverse tasks, driving the development and widespread adoption of LLM-as-a-Judge systems for automated evaluation, including red teaming and benchmarking. However, these systems are susceptible to adversarial attacks that can manipulate evaluation outcomes, raising critical concerns about their robustness and trustworthiness. Existing evaluation methods for LLM-based judges are often fragmented and lack a unified framework for comprehensive robustness assessment. Furthermore, the impact of prompt template design and model selection on judge robustness has rarely been explored, and their performance in real-world deployments remains largely unverified. To address these gaps, we introduce RobustJudge, a fully automated and modularly extensible framework designed to systematically evaluate the robustness of LLM-as-a-Judge across task datasets, judge prompt templates, judge models, attacks, and defenses. Specifically, RobustJudge investigates the effectiveness of 15 attack methods and 8 defense strategies across 13 models (RQ1), examines the impact of prompt template design and model selection (RQ2), and evaluates the security of real-world deployments (RQ3). Our study yields three main findings: (1) LLM-based judges remain susceptible under both pointwise and pairwise protocols. The combined Attack exhibits the strongest and most transferable performance among those evaluated, while the evaluated defenses exhibit no universal dominance across robustness, benign utility, and computational cost. (2) Robustness is highly sensitive to both prompt-template and judge model choices. (3) Optimization-based attack combined with long suffixes can substantially inflate scores returned by both PAI-Judge variants.

Yaguan Qian, Chenyu Zhao, Zhaoquan Gu et al.

Deep neural networks (DNNs) are vulnerable to adversarial examples crafted by well-designed perturbations. This could lead to disastrous results on critical applications such as self-driving cars, surveillance security, and medical diagnosis. At present, adversarial training is one of the most effective defenses against adversarial examples. However, traditional adversarial training makes it difficult to achieve a good trade-off between clean accuracy and robustness since spurious features are still learned by DNNs. The intrinsic reason is that traditional adversarial training makes it difficult to fully learn core features from adversarial examples when adversarial noise and clean examples cannot be disentangled. In this paper, we disentangle the adversarial examples into natural and perturbed patterns by bit-plane slicing. We assume the higher bit-planes represent natural patterns and the lower bit-planes represent perturbed patterns, respectively. We propose a Feature-Focusing Adversarial Training (F$^2$AT), which differs from previous work in that it enforces the model to focus on the core features from natural patterns and reduce the impact of spurious features from perturbed patterns. The experimental results demonstrated that F$^2$AT outperforms state-of-the-art methods in clean accuracy and adversarial robustness.

Yangkai Du, Tengfei Ma, Lingfei Wu et al.

Code Clone Detection, which aims to retrieve functionally similar programs from large code bases, has been attracting increasing attention. Modern software often involves a diverse range of programming languages. However, current code clone detection methods are generally limited to only a few popular programming languages due to insufficient annotated data as well as their own model design constraints. To address these issues, we present AdaCCD, a novel cross-lingual adaptation method that can detect cloned codes in a new language without annotations in that language. AdaCCD leverages language-agnostic code representations from pre-trained programming language models and propose an Adaptively Refined Contrastive Learning framework to transfer knowledge from resource-rich languages to resource-poor languages. We evaluate the cross-lingual adaptation results of AdaCCD by constructing a multilingual code clone detection benchmark consisting of 5 programming languages. AdaCCD achieves significant improvements over other baselines, and achieve comparable performance to supervised fine-tuning.

Yuwen Pu, Jiahao Chen, Jiayu Pan et al.

Face recognition service has been used in many fields and brings much convenience to people. However, once the user's facial data is transmitted to a service provider, the user will lose control of his/her private data. In recent years, there exist various security and privacy issues due to the leakage of facial data. Although many privacy-preserving methods have been proposed, they usually fail when they are not accessible to adversaries' strategies or auxiliary data. Hence, in this paper, by fully considering two cases of uploading facial images and facial features, which are very typical in face recognition service systems, we proposed a data privacy minimization transformation (PMT) method. This method can process the original facial data based on the shallow model of authorized services to obtain the obfuscated data. The obfuscated data can not only maintain satisfactory performance on authorized models and restrict the performance on other unauthorized models but also prevent original privacy data from leaking by AI methods and human visual theft. Additionally, since a service provider may execute preprocessing operations on the received data, we also propose an enhanced perturbation method to improve the robustness of PMT. Besides, to authorize one facial image to multiple service models simultaneously, a multiple restriction mechanism is proposed to improve the scalability of PMT. Finally, we conduct extensive experiments and evaluate the effectiveness of the proposed PMT in defending against face reconstruction, data abuse, and face attribute estimation attacks. These experimental results demonstrate that PMT performs well in preventing facial data abuse and privacy leakage while maintaining face recognition accuracy.

Guangke Chen, Yuhui Wang, Shouling Ji et al.

Modern text-to-speech (TTS) systems, particularly those built on Large Audio-Language Models (LALMs), generate high-fidelity speech that faithfully reproduces input text and mimics specified speaker identities. While prior misuse studies have focused on speaker impersonation, this work explores a distinct content-centric threat: exploiting TTS systems to produce speech containing harmful content. Realizing such threats poses two core challenges: (1) LALM safety alignment frequently rejects harmful prompts, yet existing jailbreak attacks are ill-suited for TTS because these systems are designed to faithfully vocalize any input text, and (2) real-world deployment pipelines often employ input/output filters that block harmful text and audio. We present HARMGEN, a suite of five attacks organized into two families that address these challenges. The first family employs semantic obfuscation techniques (Concat, Shuffle) that conceal harmful content within text. The second leverages audio-modality exploits (Read, Spell, Phoneme) that inject harmful content through auxiliary audio channels while maintaining benign textual prompts. Through evaluation across five commercial LALMs-based TTS systems and three datasets spanning two languages, we demonstrate that our attacks substantially reduce refusal rates and increase the toxicity of generated speech. We further assess both reactive countermeasures deployed by audio-streaming platforms and proactive defenses implemented by TTS providers. Our analysis reveals critical vulnerabilities: deepfake detectors underperform on high-fidelity audio; reactive moderation can be circumvented by adversarial perturbations; while proactive moderation detects 57-93% of attacks. Our work highlights a previously underexplored content-centric misuse vector for TTS and underscore the need for robust cross-modal safeguards throughout training and deployment.

Zhe Ma, Jianfeng Dong, Shouling Ji et al.

Visual retrieval aims to search for the most relevant visual items, e.g., images and videos, from a candidate gallery with a given query item. Accuracy and efficiency are two competing objectives in retrieval tasks. Instead of crafting a new method pursuing further improvement on accuracy, in this paper we propose a multi-teacher distillation framework Whiten-MTD, which is able to transfer knowledge from off-the-shelf pre-trained retrieval models to a lightweight student model for efficient visual retrieval. Furthermore, we discover that the similarities obtained by different retrieval models are diversified and incommensurable, which makes it challenging to jointly distill knowledge from multiple models. Therefore, we propose to whiten the output of teacher models before fusion, which enables effective multi-teacher distillation for retrieval models. Whiten-MTD is conceptually simple and practically effective. Extensive experiments on two landmark image retrieval datasets and one video retrieval dataset demonstrate the effectiveness of our proposed method, and its good balance of retrieval performance and efficiency. Our source code is released at https://github.com/Maryeon/whiten_mtd.

Linkang Du, Zheng Zhu, Min Chen et al.

Text-to-image models based on diffusion processes, such as DALL-E, Stable Diffusion, and Midjourney, are capable of transforming texts into detailed images and have widespread applications in art and design. As such, amateur users can easily imitate professional-level paintings by collecting an artist's work and fine-tuning the model, leading to concerns about artworks' copyright infringement. To tackle these issues, previous studies either add visually imperceptible perturbation to the artwork to change its underlying styles (perturbation-based methods) or embed post-training detectable watermarks in the artwork (watermark-based methods). However, when the artwork or the model has been published online, i.e., modification to the original artwork or model retraining is not feasible, these strategies might not be viable. To this end, we propose a novel method for data-use auditing in the text-to-image generation model. The general idea of ArtistAuditor is to identify if a suspicious model has been finetuned using the artworks of specific artists by analyzing the features related to the style. Concretely, ArtistAuditor employs a style extractor to obtain the multi-granularity style representations and treats artworks as samplings of an artist's style. Then, ArtistAuditor queries a trained discriminator to gain the auditing decisions. The experimental results on six combinations of models and datasets show that ArtistAuditor can achieve high AUC values (> 0.937). By studying ArtistAuditor's transferability and core modules, we provide valuable insights into the practical implementation. Finally, we demonstrate the effectiveness of ArtistAuditor in real-world cases by an online platform Scenario. ArtistAuditor is open-sourced at https://github.com/Jozenn/ArtistAuditor.

Oubo Ma, Linkang Du, Yang Dai et al.

Deep reinforcement learning (DRL) is widely applied to safety-critical decision-making scenarios. However, DRL is vulnerable to backdoor attacks, especially action-level backdoors, which pose significant threats through precise manipulation and flexible activation, risking outcomes like vehicle collisions or drone crashes. The key distinction of action-level backdoors lies in the utilization of the backdoor reward function to associate triggers with target actions. Nevertheless, existing studies typically rely on backdoor reward functions with fixed values or conditional flipping, which lack universality across diverse DRL tasks and backdoor designs, resulting in fluctuations or even failure in practice. This paper proposes the first universal action-level backdoor attack framework, called UNIDOOR, which enables adaptive exploration of backdoor reward functions through performance monitoring, eliminating the reliance on expert knowledge and grid search. We highlight that action tampering serves as a crucial component of action-level backdoor attacks in continuous action scenarios, as it addresses attack failures caused by low-frequency target actions. Extensive evaluations demonstrate that UNIDOOR significantly enhances the attack performance of action-level backdoors, showcasing its universality across diverse attack scenarios, including single/multiple agents, single/multiple backdoors, discrete/continuous action spaces, and sparse/dense reward signals. Furthermore, visualization results encompassing state distribution, neuron activation, and animations demonstrate the stealthiness of UNIDOOR. The source code of UNIDOOR can be found at https://github.com/maoubo/UNIDOOR.

Mingxuan Zhang, Oubo Ma, Kang Wei et al.

Deep reinforcement learning (DRL) has achieved remarkable success in a wide range of sequential decision-making applications, including robotics, healthcare, smart grids, and finance. Recent studies reveal that adversaries can implant backdoors into DRL agents during the training phase. These backdoors can later be activated by specific triggers during deployment, compelling the agent to execute targeted actions and potentially leading to severe consequences, such as drone crashes or vehicle collisions. However, existing backdoor attacks utilize simplistic and heuristic trigger configurations, overlooking the critical impact of trigger design on attack effectiveness. To address this gap, we introduce TooBadRL, the first framework to systematically optimize DRL backdoor triggers across three critical aspects: injection timing, trigger dimension, and manipulation magnitude. Specifically, we first introduce a performance-aware adaptive freezing mechanism to determine the injection timing during training. Then, we formulate trigger selection as an influence attribution problem and apply Shapley value analysis to identify the most influential trigger dimension for injection. Furthermore, we propose an adversarial input synthesis method to optimize the manipulation magnitude under environmental constraints. Extensive evaluations on three DRL algorithms and nine benchmark tasks demonstrate that TooBadRL outperforms five baseline methods in terms of attack success rate while only slightly affecting normal task performance. We further evaluate potential defense strategies from detection and mitigation perspectives. We open-source our code to facilitate reproducibility and further research.

Xiang Ling, Lingfei Wu, Jiangyu Zhang et al.

Malware has been one of the most damaging threats to computers that span across multiple operating systems and various file formats. To defend against ever-increasing and ever-evolving malware, tremendous efforts have been made to propose a variety of malware detection that attempt to effectively and efficiently detect malware so as to mitigate possible damages as early as possible. Recent studies have shown that, on the one hand, existing ML and DL techniques enable superior solutions in detecting newly emerging and previously unseen malware. However, on the other hand, ML and DL models are inherently vulnerable to adversarial attacks in the form of adversarial examples. In this paper, we focus on malware with the file format of portable executable (PE) in the family of Windows operating systems, namely Windows PE malware, as a representative case to study the adversarial attack methods in such adversarial settings. To be specific, we start by first outlining the general learning framework of Windows PE malware detection based on ML/DL and subsequently highlighting three unique challenges of performing adversarial attacks in the context of Windows PE malware. Then, we conduct a comprehensive and systematic review to categorize the state-of-the-art adversarial attacks against PE malware detection, as well as corresponding defenses to increase the robustness of Windows PE malware detection. Finally, we conclude the paper by first presenting other related attacks against Windows PE malware detection beyond the adversarial attacks and then shedding light on future research directions and opportunities. In addition, a curated resource list of adversarial attacks and defenses for Windows PE malware detection is also available at https://github.com/ryderling/adversarial-attacks-and-defenses-for-windows-pe-malware-detection.

Jianfeng Dong, Zhe Ma, Xiaofeng Mao et al.

This paper strives to predict fine-grained fashion similarity. In this similarity paradigm, one should pay more attention to the similarity in terms of a specific design/attribute between fashion items. For example, whether the collar designs of the two clothes are similar. It has potential value in many fashion related applications, such as fashion copyright protection. To this end, we propose an Attribute-Specific Embedding Network (ASEN) to jointly learn multiple attribute-specific embeddings, thus measure the fine-grained similarity in the corresponding space. The proposed ASEN is comprised of a global branch and a local branch. The global branch takes the whole image as input to extract features from a global perspective, while the local branch takes as input the zoomed-in region-of-interest (RoI) w.r.t. the specified attribute thus able to extract more fine-grained features. As the global branch and the local branch extract the features from different perspectives, they are complementary to each other. Additionally, in each branch, two attention modules, i.e., Attribute-aware Spatial Attention and Attribute-aware Channel Attention, are integrated to make ASEN be able to locate the related regions and capture the essential patterns under the guidance of the specified attribute, thus make the learned attribute-specific embeddings better reflect the fine-grained similarity. Extensive experiments on three fashion-related datasets, i.e., FashionAI, DARN, and DeepFashion, show the effectiveness of ASEN for fine-grained fashion similarity prediction and its potential for fashion reranking. Code and data are available at https://github.com/maryeon/asenpp .

Zhenguang Liu, Kedi Lyu, Shuang Wu et al.

Human motion prediction from historical pose sequence is at the core of many applications in machine intelligence. However, in current state-of-the-art methods, the predicted future motion is confined within the same activity. One can neither generate predictions that differ from the current activity, nor manipulate the body parts to explore various future possibilities. Undoubtedly, this greatly limits the usefulness and applicability of motion prediction. In this paper, we propose a generalization of the human motion prediction task in which control parameters can be readily incorporated to adjust the forecasted motion. Our method is compelling in that it enables manipulable motion prediction across activity types and allows customization of the human movement in a variety of fine-grained ways. To this aim, a simple yet effective composite GAN structure, consisting of local GANs for different body parts and aggregated via a global GAN is presented. The local GANs game in lower dimensions, while the global GAN adjusts in high dimensional space to avoid mode collapse. Extensive experiments show that our method outperforms state-of-the-art. The codes are available at https://github.com/herolvkd/AM-GAN.

Zhe Ma, Fenghao Liu, Jianfeng Dong et al.

This paper aims for the language-based product image retrieval task. The majority of previous works have made significant progress by designing network structure, similarity measurement, and loss function. However, they typically perform vision-text matching at certain granularity regardless of the intrinsic multiple granularities of images. In this paper, we focus on the cross-modal similarity measurement, and propose a novel Hierarchical Similarity Learning (HSL) network. HSL first learns multi-level representations of input data by stacked encoders, and object-granularity similarity and image-granularity similarity are computed at each level. All the similarities are combined as the final hierarchical cross-modal similarity. Experiments on a large-scale product retrieval dataset demonstrate the effectiveness of our proposed method. Code and data are available at https://github.com/liufh1/hsl.

Ren Pang, Zheng Zhang, Xiangshan Gao et al.

Neural backdoors represent one primary threat to the security of deep learning systems. The intensive research has produced a plethora of backdoor attacks/defenses, resulting in a constant arms race. However, due to the lack of evaluation benchmarks, many critical questions remain under-explored: (i) what are the strengths and limitations of different attacks/defenses? (ii) what are the best practices to operate them? and (iii) how can the existing attacks/defenses be further improved? To bridge this gap, we design and implement TROJANZOO, the first open-source platform for evaluating neural backdoor attacks/defenses in a unified, holistic, and practical manner. Thus far, focusing on the computer vision domain, it has incorporated 8 representative attacks, 14 state-of-the-art defenses, 6 attack performance metrics, 10 defense utility metrics, as well as rich tools for in-depth analysis of the attack-defense interactions. Leveraging TROJANZOO, we conduct a systematic study on the existing attacks/defenses, unveiling their complex design spectrum: both manifest intricate trade-offs among multiple desiderata (e.g., the effectiveness, evasiveness, and transferability of attacks). We further explore improving the existing attacks/defenses, leading to a number of interesting findings: (i) one-pixel triggers often suffice; (ii) training from scratch often outperforms perturbing benign models to craft trojan models; (iii) optimizing triggers and trojan models jointly greatly improves both attack effectiveness and evasiveness; (iv) individual defenses can often be evaded by adaptive attacks; and (v) exploiting model interpretability significantly improves defense robustness. We envision that TROJANZOO will serve as a valuable platform to facilitate future research on neural backdoors.

Yuwei Li, Shouling Ji, Yuan Chen et al.

A flurry of fuzzing tools (fuzzers) have been proposed in the literature, aiming at detecting software vulnerabilities effectively and efficiently. To date, it is however still challenging to compare fuzzers due to the inconsistency of the benchmarks, performance metrics, and/or environments for evaluation, which buries the useful insights and thus impedes the discovery of promising fuzzing primitives. In this paper, we design and develop UNIFUZZ, an open-source and metrics-driven platform for assessing fuzzers in a comprehensive and quantitative manner. Specifically, UNIFUZZ to date has incorporated 35 usable fuzzers, a benchmark of 20 real-world programs, and six categories of performance metrics. We first systematically study the usability of existing fuzzers, find and fix a number of flaws, and integrate them into UNIFUZZ. Based on the study, we propose a collection of pragmatic performance metrics to evaluate fuzzers from six complementary perspectives. Using UNIFUZZ, we conduct in-depth evaluations of several prominent fuzzers including AFL [1], AFLFast [2], Angora [3], Honggfuzz [4], MOPT [5], QSYM [6], T-Fuzz [7] and VUzzer64 [8]. We find that none of them outperforms the others across all the target programs, and that using a single metric to assess the performance of a fuzzer may lead to unilateral conclusions, which demonstrates the significance of comprehensive metrics. Moreover, we identify and investigate previously overlooked factors that may significantly affect a fuzzer's performance, including instrumentation methods and crash analysis tools. Our empirical results show that they are critical to the evaluation of a fuzzer. We hope that our findings can shed light on reliable fuzzing evaluation, so that we can discover promising fuzzing primitives to effectively facilitate fuzzer designs in the future.

Chenghui Shi, Xiaogang Xu, Shouling Ji et al.

Following the principle of to set one's own spear against one's own shield, we study how to design adversarial CAPTCHAs in this paper. We first identify the similarity and difference between adversarial CAPTCHA generation and existing hot adversarial example (image) generation research. Then, we propose a framework for text-based and image-based adversarial CAPTCHA generation on top of state-of-the-art adversarial image generation techniques. Finally, we design and implement an adversarial CAPTCHA generation and evaluation system, named aCAPTCHA, which integrates 10 image preprocessing techniques, 9 CAPTCHA attacks, 4 baseline adversarial CAPTCHA generation methods, and 8 new adversarial CAPTCHA generation methods. To examine the performance of aCAPTCHA, extensive security and usability evaluations are conducted. The results demonstrate that the generated adversarial CAPTCHAs can significantly improve the security of normal CAPTCHAs while maintaining similar usability. To facilitate the CAPTCHA security research, we also open source the aCAPTCHA system, including the source code, trained models, datasets, and the usability evaluation interfaces.

Chenyang Lyu, Shouling Ji, Yuwei Li et al.

Fuzzing is an automated application vulnerability detection method. For genetic algorithm-based fuzzing, it can mutate the seed files provided by users to obtain a number of inputs, which are then used to test the objective application in order to trigger potential crashes. As shown in existing literature, the seed file selection is crucial for the efficiency of fuzzing. However, current seed selection strategies do not seem to be better than randomly picking seed files. Therefore, in this paper, we propose a novel and generic system, named SmartSeed, to generate seed files towards efficient fuzzing. Specifically, SmartSeed is designed based on a machine learning model to learn and generate high-value binary seeds. We evaluate SmartSeed along with American Fuzzy Lop (AFL) on 12 open-source applications with the input formats of mp3, bmp or flv. We also combine SmartSeed with different fuzzing tools to examine its compatibility. From extensive experiments, we find that SmartSeed has the following advantages: First, it only requires tens of seconds to generate sufficient high-value seeds. Second, it can generate seeds with multiple kinds of input formats and significantly improves the fuzzing performance for most applications with the same input format. Third, SmartSeed is compatible to different fuzzing tools. In total, our system discovers more than twice unique crashes and 5,040 extra unique paths than the existing best seed selection strategy for the evaluated 12 applications. From the crashes found by SmartSeed, we discover 16 new vulnerabilities and have received their CVE IDs.

Zehan Zhu, Heng Zhao, Yan Huang et al.

In this paper, we propose a Differentially Private Stochastic Gradient Push with Compressed communication (termed DP-CSGP) for decentralized learning over directed graphs. Different from existing works, the proposed algorithm is designed to maintain high model utility while ensuring both rigorous differential privacy (DP) guarantees and efficient communication. For general non-convex and smooth objective functions, we show that the proposed algorithm achieves a tight utility bound of $\mathcal{O}\left( \sqrt{d\log \left( \frac{1}δ \right)}/(\sqrt{n}Jε) \right)$ ($J$ and $d$ are the number of local samples and the dimension of decision variables, respectively) with $\left(ε, δ\right)$-DP guarantee for each node, matching that of decentralized counterparts with exact communication. Extensive experiments on benchmark tasks show that, under the same privacy budget, DP-CSGP achieves comparable model accuracy with significantly lower communication cost than existing decentralized counterparts with exact communication.

Yuyou Gan, Yong Yang, Zhe Ma et al.

With the continuous development of large language models (LLMs), transformer-based models have made groundbreaking advances in numerous natural language processing (NLP) tasks, leading to the emergence of a series of agents that use LLMs as their control hub. While LLMs have achieved success in various tasks, they face numerous security and privacy threats, which become even more severe in the agent scenarios. To enhance the reliability of LLM-based applications, a range of research has emerged to assess and mitigate these risks from different perspectives. To help researchers gain a comprehensive understanding of various risks, this survey collects and analyzes the different threats faced by these agents. To address the challenges posed by previous taxonomies in handling cross-module and cross-stage threats, we propose a novel taxonomy framework based on the sources and impacts. Additionally, we identify six key features of LLM-based agents, based on which we summarize the current research progress and analyze their limitations. Subsequently, we select four representative agents as case studies to analyze the risks they may face in practical use. Finally, based on the aforementioned analyses, we propose future research directions from the perspectives of data, methodology, and policy, respectively.

Mingqi Lv, HongZhe Gao, Xuebo Qiu et al.

APT (Advanced Persistent Threat) with the characteristics of persistence, stealth, and diversity is one of the greatest threats against cyber-infrastructure. As a countermeasure, existing studies leverage provenance graphs to capture the complex relations between system entities in a host for effective APT detection. In addition to detecting single attack events as most existing work does, understanding the tactics / techniques (e.g., Kill-Chain, ATT&CK) applied to organize and accomplish the APT attack campaign is more important for security operations. Existing studies try to manually design a set of rules to map low-level system events to high-level APT tactics / techniques. However, the rule based methods are coarse-grained and lack generalization ability, thus they can only recognize APT tactics and cannot identify fine-grained APT techniques and mutant APT attacks. In this paper, we propose TREC, the first attempt to recognize APT tactics / techniques from provenance graphs by exploiting deep learning techniques. To address the "needle in a haystack" problem, TREC segments small and compact subgraphs covering individual APT technique instances from a large provenance graph based on a malicious node detection model and a subgraph sampling algorithm. To address the "training sample scarcity" problem, TREC trains the APT tactic / technique recognition model in a few-shot learning manner by adopting a Siamese neural network. We evaluate TREC based on a customized dataset collected and made public by our team. The experiment results show that TREC significantly outperforms state-of-the-art systems in APT tactic recognition and TREC can also effectively identify APT techniques.

Oubo Ma, Yuwen Pu, Linkang Du et al.

Recent advancements in multi-agent reinforcement learning (MARL) have opened up vast application prospects, such as swarm control of drones, collaborative manipulation by robotic arms, and multi-target encirclement. However, potential security threats during the MARL deployment need more attention and thorough investigation. Recent research reveals that attackers can rapidly exploit the victim's vulnerabilities, generating adversarial policies that result in the failure of specific tasks. For instance, reducing the winning rate of a superhuman-level Go AI to around 20%. Existing studies predominantly focus on two-player competitive environments, assuming attackers possess complete global state observation. In this study, we unveil, for the first time, the capability of attackers to generate adversarial policies even when restricted to partial observations of the victims in multi-agent competitive environments. Specifically, we propose a novel black-box attack (SUB-PLAY) that incorporates the concept of constructing multiple subgames to mitigate the impact of partial observability and suggests sharing transitions among subpolicies to improve attackers' exploitative ability. Extensive evaluations demonstrate the effectiveness of SUB-PLAY under three typical partial observability limitations. Visualization results indicate that adversarial policies induce significantly different activations of the victims' policy networks. Furthermore, we evaluate three potential defenses aimed at exploring ways to mitigate security threats posed by adversarial policies, providing constructive recommendations for deploying MARL in competitive environments.

Yang Dai, Oubo Ma, Longfei Zhang et al.

Transformer-based trajectory optimization methods have demonstrated exceptional performance in offline Reinforcement Learning (offline RL). Yet, it poses challenges due to substantial parameter size and limited scalability, which is particularly critical in sequential decision-making scenarios where resources are constrained such as in robots and drones with limited computational power. Mamba, a promising new linear-time sequence model, offers performance on par with transformers while delivering substantially fewer parameters on long sequences. As it remains unclear whether Mamba is compatible with trajectory optimization, this work aims to conduct comprehensive experiments to explore the potential of Decision Mamba (dubbed DeMa) in offline RL from the aspect of data structures and essential components with the following insights: (1) Long sequences impose a significant computational burden without contributing to performance improvements since DeMa's focus on sequences diminishes approximately exponentially. Consequently, we introduce a Transformer-like DeMa as opposed to an RNN-like DeMa. (2) For the components of DeMa, we identify the hidden attention mechanism as a critical factor in its success, which can also work well with other residual structures and does not require position embedding. Extensive evaluations demonstrate that our specially designed DeMa is compatible with trajectory optimization and surpasses previous methods, outperforming Decision Transformer (DT) with higher performance while using 30\% fewer parameters in Atari, and exceeding DT with only a quarter of the parameters in MuJoCo.

Changjiang Li, Ren Pang, Bochuan Cao et al.

Recent studies have shown that contrastive learning, like supervised learning, is highly vulnerable to backdoor attacks wherein malicious functions are injected into target models, only to be activated by specific triggers. However, thus far it remains under-explored how contrastive backdoor attacks fundamentally differ from their supervised counterparts, which impedes the development of effective defenses against the emerging threat. This work represents a solid step toward answering this critical question. Specifically, we define TRL, a unified framework that encompasses both supervised and contrastive backdoor attacks. Through the lens of TRL, we uncover that the two types of attacks operate through distinctive mechanisms: in supervised attacks, the learning of benign and backdoor tasks tends to occur independently, while in contrastive attacks, the two tasks are deeply intertwined both in their representations and throughout their learning processes. This distinction leads to the disparate learning dynamics and feature distributions of supervised and contrastive attacks. More importantly, we reveal that the specificities of contrastive backdoor attacks entail important implications from a defense perspective: existing defenses for supervised attacks are often inadequate and not easily retrofitted to contrastive attacks. We also explore several alternative defenses and discuss their potential challenges. Our findings highlight the need for defenses tailored to the specificities of contrastive backdoor attacks, pointing to promising directions for future research.

Hengyu An, Jinghuai Zhang, Tianyu Du et al.

Large language model (LLM) agents are widely deployed in real-world applications, where they leverage tools to retrieve and manipulate external data for complex tasks. However, when interacting with untrusted data sources (e.g., fetching information from public websites), tool responses may contain injected instructions that covertly influence agent behaviors and lead to malicious outcomes, a threat referred to as Indirect Prompt Injection (IPI). Existing defenses typically rely on advanced prompting strategies or auxiliary detection models. While these methods have demonstrated some effectiveness, they fundamentally rely on assumptions about the model's inherent security, which lacks structural constraints on agent behaviors. As a result, agents still retain unrestricted access to tool invocations, leaving them vulnerable to stronger attack vectors that can bypass the security guardrails of the model. To prevent malicious tool invocations at the source, we propose a novel defensive task execution paradigm, called IPIGuard, which models the agents' task execution process as a traversal over a planned Tool Dependency Graph (TDG). By explicitly decoupling action planning from interaction with external data, IPIGuard significantly reduces unintended tool invocations triggered by injected instructions, thereby enhancing robustness against IPI attacks. Experiments on the AgentDojo benchmark show that IPIGuard achieves a superior balance between effectiveness and robustness, paving the way for the development of safer agentic systems in dynamic environments.

Zeyu Li, Chenghui Shi, Yuwen Pu et al.

The widespread use of deep learning technology across various industries has made deep neural network models highly valuable and, as a result, attractive targets for potential attackers. Model extraction attacks, particularly query-based model extraction attacks, allow attackers to replicate a substitute model with comparable functionality to the victim model and present a significant threat to the confidentiality and security of MLaaS platforms. While many studies have explored threats of model extraction attacks against classification models in recent years, object detection models, which are more frequently used in real-world scenarios, have received less attention. In this paper, we investigate the challenges and feasibility of query-based model extraction attacks against object detection models and propose an effective attack method called MEAOD. It selects samples from the attacker-possessed dataset to construct an efficient query dataset using active learning and enhances the categories with insufficient objects. We additionally improve the extraction effectiveness by updating the annotations of the query dataset. According to our gray-box and black-box scenarios experiments, we achieve an extraction performance of over 70% under the given condition of a 10k query budget.