Guowen Xu

Guanlin Li, Guowen Xu, Tianwei Zhang

In this paper, we study adversarial training on datasets that obey the long-tailed distribution, which is practical but rarely explored in previous works. Compared with conventional adversarial training on balanced datasets, this process falls into the dilemma of generating uneven adversarial examples (AEs) and an unbalanced feature embedding space, causing the resulting model to exhibit low robustness and accuracy on tail data. To combat that, we theoretically analyze the lower bound of the robust risk to train a model on a long-tailed dataset to obtain the key challenges in addressing the aforementioned dilemmas. Based on it, we propose a new adversarial training framework -- Re-balancing Adversarial Training (REAT). This framework consists of two components: (1) a new training strategy inspired by the effective number to guide the model to generate more balanced and informative AEs; (2) a carefully constructed penalty function to force a satisfactory feature space. Evaluation results on different datasets and model structures prove that REAT can effectively enhance the model's robustness and preserve the model's clean accuracy. The code can be found in https://github.com/GuanlinLee/REAT.

Xingshuo Han, Guowen Xu, Yuan Zhou et al.

Modern autonomous vehicles adopt state-of-the-art DNN models to interpret the sensor data and perceive the environment. However, DNN models are vulnerable to different types of adversarial attacks, which pose significant risks to the security and safety of the vehicles and passengers. One prominent threat is the backdoor attack, where the adversary can compromise the DNN model by poisoning the training samples. Although lots of effort has been devoted to the investigation of the backdoor attack to conventional computer vision tasks, its practicality and applicability to the autonomous driving scenario is rarely explored, especially in the physical world. In this paper, we target the lane detection system, which is an indispensable module for many autonomous driving tasks, e.g., navigation, lane switching. We design and realize the first physical backdoor attacks to such system. Our attacks are comprehensively effective against different types of lane detection algorithms. Specifically, we introduce two attack methodologies (poison-annotation and clean-annotation) to generate poisoned samples. With those samples, the trained lane detection model will be infected with the backdoor, and can be activated by common objects (e.g., traffic cones) to make wrong detections, leading the vehicle to drive off the road or onto the opposite lane. Extensive evaluations on public datasets and physical autonomous vehicles demonstrate that our backdoor attacks are effective, stealthy and robust against various defense solutions. Our codes and experimental videos can be found in https://sites.google.com/view/lane-detection-attack/lda.

Guanlin Li, Guowen Xu, Tianwei Zhang

In this paper, we consider the instance segmentation task on a long-tailed dataset, which contains label noise, i.e., some of the annotations are incorrect. There are two main reasons making this case realistic. First, datasets collected from real world usually obey a long-tailed distribution. Second, for instance segmentation datasets, as there are many instances in one image and some of them are tiny, it is easier to introduce noise into the annotations. Specifically, we propose a new dataset, which is a large vocabulary long-tailed dataset containing label noise for instance segmentation. Furthermore, we evaluate previous proposed instance segmentation algorithms on this dataset. The results indicate that the noise in the training dataset will hamper the model in learning rare categories and decrease the overall performance, and inspire us to explore more effective approaches to address this practical challenge. The code and dataset are available in https://github.com/GuanlinLee/Noisy-LVIS.

Xiaobei Yan, Xiaoxuan Lou, Guowen Xu et al.

DNN accelerators have been widely deployed in many scenarios to speed up the inference process and reduce the energy consumption. One big concern about the usage of the accelerators is the confidentiality of the deployed models: model inference execution on the accelerators could leak side-channel information, which enables an adversary to preciously recover the model details. Such model extraction attacks can not only compromise the intellectual property of DNN models, but also facilitate some adversarial attacks. Although previous works have demonstrated a number of side-channel techniques to extract models from DNN accelerators, they are not practical for two reasons. (1) They only target simplified accelerator implementations, which have limited practicality in the real world. (2) They require heavy human analysis and domain knowledge. To overcome these limitations, this paper presents Mercury, the first automated remote side-channel attack against the off-the-shelf Nvidia DNN accelerator. The key insight of Mercury is to model the side-channel extraction process as a sequence-to-sequence problem. The adversary can leverage a time-to-digital converter (TDC) to remotely collect the power trace of the target model's inference. Then he uses a learning model to automatically recover the architecture details of the victim model from the power trace without any prior knowledge. The adversary can further use the attention mechanism to localize the leakage points that contribute most to the attack. Evaluation results indicate that Mercury can keep the error rate of model extraction below 1%.

Senkang Hu, Zhengru Fang, Haonan An et al.

Collaborative perception among multiple connected and autonomous vehicles can greatly enhance perceptive capabilities by allowing vehicles to exchange supplementary information via communications. Despite advances in previous approaches, challenges still remain due to channel variations and data heterogeneity among collaborative vehicles. To address these issues, we propose ACC-DA, a channel-aware collaborative perception framework to dynamically adjust the communication graph and minimize the average transmission delay while mitigating the side effects from the data heterogeneity. Our novelties lie in three aspects. We first design a transmission delay minimization method, which can construct the communication graph and minimize the transmission delay according to different channel information state. We then propose an adaptive data reconstruction mechanism, which can dynamically adjust the rate-distortion trade-off to enhance perception efficiency. Moreover, it minimizes the temporal redundancy during data transmissions. Finally, we conceive a domain alignment scheme to align the data distribution from different vehicles, which can mitigate the domain gap between different vehicles and improve the performance of the target task. Comprehensive experiments demonstrate the effectiveness of our method in comparison to the existing state-of-the-art works.

Wenbo Jiang, Hongwei Li, Jiaming He et al.

Recently, deep learning-based Image-to-Image (I2I) networks have become the predominant choice for I2I tasks such as image super-resolution and denoising. Despite their remarkable performance, the backdoor vulnerability of I2I networks has not been explored. To fill this research gap, we conduct a comprehensive investigation on the susceptibility of I2I networks to backdoor attacks. Specifically, we propose a novel backdoor attack technique, where the compromised I2I network behaves normally on clean input images, yet outputs a predefined image of the adversary for malicious input images containing the trigger. To achieve this I2I backdoor attack, we propose a targeted universal adversarial perturbation (UAP) generation algorithm for I2I networks, where the generated UAP is used as the backdoor trigger. Additionally, in the backdoor training process that contains the main task and the backdoor task, multi-task learning (MTL) with dynamic weighting methods is employed to accelerate convergence rates. In addition to attacking I2I tasks, we extend our I2I backdoor to attack downstream tasks, including image classification and object detection. Extensive experiments demonstrate the effectiveness of the I2I backdoor on state-of-the-art I2I network architectures, as well as the robustness against different mainstream backdoor defenses.

Jiaming He, Guanyu Hou, Hongwei Li et al.

Text-to-Video (T2V) models are capable of synthesizing high-quality, temporally coherent dynamic video content, but the diverse generation also inherently introduces critical safety challenges. Existing safety evaluation methods,which focus on static image and text generation, are insufficient to capture the complex temporal dynamics in video generation. To address this, we propose a TEmporal-aware Automated Red-teaming framework, named TEAR, an automated framework designed to uncover safety risks specifically linked to the dynamic temporal sequencing of T2V models. TEAR employs a temporal-aware test generator optimized via a two-stage approach: initial generator training and temporal-aware online preference learning, to craft textually innocuous prompts that exploit temporal dynamics to elicit policy-violating video output. And a refine model is adopted to improve the prompt stealthiness and adversarial effectiveness cyclically. Extensive experimental evaluation demonstrates the effectiveness of TEAR across open-source and commercial T2V systems with over 80% attack success rate, a significant boost from prior best result of 57%.

Xiaoxuan Lou, Guowen Xu, Kangjie Chen et al.

Multiplication-less neural networks significantly reduce the time and energy cost on the hardware platform, as the compute-intensive multiplications are replaced with lightweight bit-shift operations. However, existing bit-shift networks are all directly transferred from state-of-the-art convolutional neural networks (CNNs), which lead to non-negligible accuracy drop or even failure of model convergence. To combat this, we propose ShiftNAS, the first framework tailoring Neural Architecture Search (NAS) to substantially reduce the accuracy gap between bit-shift neural networks and their real-valued counterparts. Specifically, we pioneer dragging NAS into a shift-oriented search space and endow it with the robust topology-related search strategy and custom regularization and stabilization. As a result, our ShiftNAS breaks through the incompatibility of traditional NAS methods for bit-shift neural networks and achieves more desirable performance in terms of accuracy and convergence. Extensive experiments demonstrate that ShiftNAS sets a new state-of-the-art for bit-shift neural networks, where the accuracy increases (1.69-8.07)% on CIFAR10, (5.71-18.09)% on CIFAR100 and (4.36-67.07)% on ImageNet, especially when many conventional CNNs fail to converge on ImageNet with bit-shift weights.

Hangcheng Cao, Longzhi Yuan, Guowen Xu et al.

Traffic sign recognition systems play a crucial role in assisting drivers to make informed decisions while driving. However, due to the heavy reliance on deep learning technologies, particularly for future connected and autonomous driving, these systems are susceptible to adversarial attacks that pose significant safety risks to both personal and public transportation. Notably, researchers recently identified a new attack vector to deceive sign recognition systems: projecting well-designed adversarial light patches onto traffic signs. In comparison with traditional adversarial stickers or graffiti, these emerging light patches exhibit heightened aggression due to their ease of implementation and outstanding stealthiness. To effectively counter this security threat, we propose a universal image inpainting mechanism, namely, SafeSign. It relies on attention-enabled multi-view image fusion to repair traffic signs contaminated by adversarial light patches, thereby ensuring the accurate sign recognition. Here, we initially explore the fundamental impact of malicious light patches on the local and global feature spaces of authentic traffic signs. Then, we design a binary mask-based U-Net image generation pipeline outputting diverse contaminated sign patterns, to provide our image inpainting model with needed training data. Following this, we develop an attention mechanism-enabled neural network to jointly utilize the complementary information from multi-view images to repair contaminated signs. Finally, extensive experiments are conducted to evaluate SafeSign's effectiveness in resisting potential light patch-based attacks, bringing an average accuracy improvement of 54.8% in three widely-used sign recognition models

Shuai Yuan, Xingshuo Han, Hongwei Li et al.

Recently, traffic sign recognition (TSR) systems have become a prominent target for physical adversarial attacks. These attacks typically rely on conspicuous stickers and projections, or using invisible light and acoustic signals that can be easily blocked. In this paper, we introduce a novel attack medium, i.e., fluorescent ink, to design a stealthy and effective physical adversarial patch, namely FIPatch, to advance the state-of-the-art. Specifically, we first model the fluorescence effect in the digital domain to identify the optimal attack settings, which guide the real-world fluorescence parameters. By applying a carefully designed fluorescence perturbation to the target sign, the attacker can later trigger a fluorescent effect using invisible ultraviolet light, causing the TSR system to misclassify the sign and potentially leading to traffic accidents. We conducted a comprehensive evaluation to investigate the effectiveness of FIPatch, which shows a success rate of 98.31% in low-light conditions. Furthermore, our attack successfully bypasses five popular defenses and achieves a success rate of 96.72%.

Haolin Wu, Jing Chen, Ruiying Du et al.

The increasing prevalence of audio deepfakes poses significant security threats, necessitating robust detection methods. While existing detection systems exhibit promise, their robustness against malicious audio manipulations remains underexplored. To bridge the gap, we undertake the first comprehensive study of the susceptibility of the most widely adopted audio deepfake detectors to manipulation attacks. Surprisingly, even manipulations like volume control can significantly bypass detection without affecting human perception. To address this, we propose CLAD (Contrastive Learning-based Audio deepfake Detector) to enhance the robustness against manipulation attacks. The key idea is to incorporate contrastive learning to minimize the variations introduced by manipulations, therefore enhancing detection robustness. Additionally, we incorporate a length loss, aiming to improve the detection accuracy by clustering real audios more closely in the feature space. We comprehensively evaluated the most widely adopted audio deepfake detection models and our proposed CLAD against various manipulation attacks. The detection models exhibited vulnerabilities, with FAR rising to 36.69%, 31.23%, and 51.28% under volume control, fading, and noise injection, respectively. CLAD enhanced robustness, reducing the FAR to 0.81% under noise injection and consistently maintaining an FAR below 1.63% across all tests. Our source code and documentation are available in the artifact repository (https://github.com/CLAD23/CLAD).

Senkang Hu, Yihang Tao, Guowen Xu et al.

Collaborative Perception (CP) has shown a promising technique for autonomous driving, where multiple connected and autonomous vehicles (CAVs) share their perception information to enhance the overall perception performance and expand the perception range. However, in CP, ego CAV needs to receive messages from its collaborators, which makes it easy to be attacked by malicious agents. For example, a malicious agent can send harmful information to the ego CAV to mislead it. To address this critical issue, we propose a novel method, CP-Guard, a tailored defense mechanism for CP that can be deployed by each agent to accurately detect and eliminate malicious agents in its collaboration network. Our key idea is to enable CP to reach a consensus rather than a conflict against the ego CAV's perception results. Based on this idea, we first develop a probability-agnostic sample consensus (PASAC) method to effectively sample a subset of the collaborators and verify the consensus without prior probabilities of malicious agents. Furthermore, we define a collaborative consistency loss (CCLoss) to capture the discrepancy between the ego CAV and its collaborators, which is used as a verification criterion for consensus. Finally, we conduct extensive experiments in collaborative bird's eye view (BEV) tasks and our results demonstrate the effectiveness of our CP-Guard. Code is available at https://github.com/CP-Security/CP-Guard

Rui Zhang, Hongwei Li, Yun Shen et al.

The deployment of large language models (LLMs) raises significant ethical and safety concerns. While LLM alignment techniques are adopted to improve model safety and trustworthiness, adversaries can exploit these techniques to undermine safety for malicious purposes, resulting in \emph{misalignment}. Misaligned LLMs may be published on open platforms to magnify harm. To address this, additional safety alignment, referred to as \emph{realignment}, is necessary before deploying untrusted third-party LLMs. This study explores the efficacy of fine-tuning methods in terms of misalignment, realignment, and the effects of their interplay. By evaluating four Supervised Fine-Tuning (SFT) and two Preference Fine-Tuning (PFT) methods across four popular safety-aligned LLMs, we reveal a mechanism asymmetry between attack and defense. While Odds Ratio Preference Optimization (ORPO) is most effective for misalignment, Direct Preference Optimization (DPO) excels in realignment, albeit at the expense of model utility. Additionally, we identify model-specific resistance, residual effects of multi-round adversarial dynamics, and other noteworthy findings. These findings highlight the need for robust safeguards and customized safety alignment strategies to mitigate potential risks in the deployment of LLMs. Our code is available at https://github.com/zhangrui4041/The-Art-of-Mis-alignment.

Senkang Hu, Yihang Tao, Guowen Xu et al.

Collaborative Perception (CP) has been shown to be a promising technique for multi-agent autonomous driving and multi-agent robotic systems, where multiple agents share their perception information to enhance the overall perception performance and expand the perception range. However, in CP, an ego agent needs to receive messages from its collaborators, which makes it vulnerable to attacks from malicious agents. To address this critical issue, we propose a unified, probability-agnostic, and adaptive framework, namely, CP-uniGuard, which is a tailored defense mechanism for CP deployed by each agent to accurately detect and eliminate malicious agents in its collaboration network. Our key idea is to enable CP to reach a consensus rather than a conflict against an ego agent's perception results. Based on this idea, we first develop a probability-agnostic sample consensus (PASAC) method to effectively sample a subset of the collaborators and verify the consensus without prior probabilities of malicious agents. Furthermore, we define collaborative consistency loss (CCLoss) for object detection task and bird's eye view (BEV) segmentation task to capture the discrepancy between an ego agent and its collaborators, which is used as a verification criterion for consensus. In addition, we propose online adaptive threshold via dual sliding windows to dynamically adjust the threshold for consensus verification and ensure the reliability of the systems in dynamic environments. Finally, we conduct extensive experiments and demonstrate the effectiveness of our framework. Code will be released at https://github.com/CP-Security/CP-uniGuard.

Rui Zhang, Zihan Wang, Tianli Yang et al.

Vision-Language Models (VLMs) are increasingly deployed in real-world applications, but their high inference cost makes them vulnerable to resource consumption attacks. Prior attacks attempt to extend VLM output sequences by optimizing adversarial images, thereby increasing inference costs. However, these extended outputs often introduce irrelevant abnormal content, compromising attack stealthiness. This trade-off between effectiveness and stealthiness poses a major limitation for existing attacks. To address this challenge, we propose \textit{Hidden Tail}, a stealthy resource consumption attack that crafts prompt-agnostic adversarial images, inducing VLMs to generate maximum-length outputs by appending special tokens invisible to users. Our method employs a composite loss function that balances semantic preservation, repetitive special token induction, and suppression of the end-of-sequence (EOS) token, optimized via a dynamic weighting strategy. Extensive experiments show that \textit{Hidden Tail} outperforms existing attacks, increasing output length by up to 19.2$\times$ and reaching the maximum token limit, while preserving attack stealthiness. These results highlight the urgent need to improve the robustness of VLMs against efficiency-oriented adversarial threats. Our code is available at https://github.com/zhangrui4041/Hidden_Tail.

Kun Wang, Guibin Zhang, Zhenhong Zhou et al. · mit

The remarkable success of Large Language Models (LLMs) has illuminated a promising pathway toward achieving Artificial General Intelligence for both academic and industrial communities, owing to their unprecedented performance across various applications. As LLMs continue to gain prominence in both research and commercial domains, their security and safety implications have become a growing concern, not only for researchers and corporations but also for every nation. Currently, existing surveys on LLM safety primarily focus on specific stages of the LLM lifecycle, e.g., deployment phase or fine-tuning phase, lacking a comprehensive understanding of the entire "lifechain" of LLMs. To address this gap, this paper introduces, for the first time, the concept of "full-stack" safety to systematically consider safety issues throughout the entire process of LLM training, deployment, and eventual commercialization. Compared to the off-the-shelf LLM safety surveys, our work demonstrates several distinctive advantages: (I) Comprehensive Perspective. We define the complete LLM lifecycle as encompassing data preparation, pre-training, post-training, deployment and final commercialization. To our knowledge, this represents the first safety survey to encompass the entire lifecycle of LLMs. (II) Extensive Literature Support. Our research is grounded in an exhaustive review of over 800+ papers, ensuring comprehensive coverage and systematic organization of security issues within a more holistic understanding. (III) Unique Insights. Through systematic literature analysis, we have developed reliable roadmaps and perspectives for each chapter. Our work identifies promising research directions, including safety in data generation, alignment techniques, model editing, and LLM-based agent systems. These insights provide valuable guidance for researchers pursuing future work in this field.

Cong Wu, Jing Chen, Qianru Fang et al.

Transfer learning, successful in knowledge translation across related tasks, faces a substantial privacy threat from membership inference attacks (MIAs). These attacks, despite posing significant risk to ML model's training data, remain limited-explored in transfer learning. The interaction between teacher and student models in transfer learning has not been thoroughly explored in MIAs, potentially resulting in an under-examined aspect of privacy vulnerabilities within transfer learning. In this paper, we propose a new MIA vector against transfer learning, to determine whether a specific data point was used to train the teacher model while only accessing the student model in a white-box setting. Our method delves into the intricate relationship between teacher and student models, analyzing the discrepancies in hidden layer representations between the student model and its shadow counterpart. These identified differences are then adeptly utilized to refine the shadow model's training process and to inform membership inference decisions effectively. Our method, evaluated across four datasets in diverse transfer learning tasks, reveals that even when an attacker only has access to the student model, the teacher model's training data remains susceptible to MIAs. We believe our work unveils the unexplored risk of membership inference in transfer learning.

Yuang Zhang, Haonan An, Zhengru Fang et al.

In recent years, autonomous driving has garnered significant attention due to its potential for improving road safety through collaborative perception among connected and autonomous vehicles (CAVs). However, time-varying channel variations in vehicular transmission environments demand dynamic allocation of communication resources. Moreover, in the context of collaborative perception, it is important to recognize that not all CAVs contribute valuable data, and some CAV data even have detrimental effects on collaborative perception. In this paper, we introduce SmartCooper, an adaptive collaborative perception framework that incorporates communication optimization and a judger mechanism to facilitate CAV data fusion. Our approach begins with optimizing the connectivity of vehicles while considering communication constraints. We then train a learnable encoder to dynamically adjust the compression ratio based on the channel state information (CSI). Subsequently, we devise a judger mechanism to filter the detrimental image data reconstructed by adaptive decoders. We evaluate the effectiveness of our proposed algorithm on the OpenCOOD platform. Our results demonstrate a substantial reduction in communication costs by 23.10\% compared to the non-judger scheme. Additionally, we achieve a significant improvement on the average precision of Intersection over Union (AP@IoU) by 7.15\% compared with state-of-the-art schemes.

Zihan Wang, Rui Zhang, Yu Liu et al.

LLM agents increasingly rely on skills to encapsulate reusable capabilities via progressively disclosed instructions. High-quality skills inject expert knowledge into general-purpose models, improving performance on specialized tasks. This quality and ease of dissemination drive the emergence of a skill economy: free skill marketplaces already report 90368 published skills, while paid marketplaces report more than 2000 listings and over $100,000 in creator earnings. Yet this growing marketplace also creates a new attack surface, as adversaries can interact with public agent to extract hidden proprietary skill content. We present the first empirical study of black-box skill stealing against LLM agent systems. To study this threat, we first derive an attack taxonomy from prior prompt-stealing methods and build an automated stealing prompt generation agent. This agent starts from model-generated seed prompts, expands them through scenario rationalization and structure injection, and enforces diversity via embedding filtering. This process yields a reproducible pipeline for evaluating agent systems. We evaluate such attacks across 3 commercial agent architectures and 5 LLMs. Our results show that agent skills can be extracted with only 3 interactions, posing a serious copyright risk. To mitigate this threat, we design defenses across three stages of the agent pipeline: input, inference, and output. Although these defenses achieve strong results, the attack remains inexpensive and readily automatable, allowing an adversary to launch repeated attempts with different variants; only one successful attempt is sufficient to compromise the protected skill. Overall, our findings suggest that these copyright risks are largely overlooked across proprietary agent ecosystems. We therefore advocate for more robust defense strategies that provide stronger protection guarantees.

Senkang Hu, Yihang Tao, Zihan Fang et al.

Collaborative perception (CP) is a promising method for safe connected and autonomous driving, which enables multiple vehicles to share sensing information to enhance perception performance. However, compared with single-vehicle perception, the openness of a CP system makes it more vulnerable to malicious attacks that can inject malicious information to mislead the perception of an ego vehicle, resulting in severe risks for safe driving. To mitigate such vulnerability, we first propose a new paradigm for malicious agent detection that effectively identifies malicious agents at the feature level without requiring verification of final perception results, significantly reducing computational overhead. Building on this paradigm, we introduce CP-GuardBench, the first comprehensive dataset provided to train and evaluate various malicious agent detection methods for CP systems. Furthermore, we develop a robust defense method called CP-Guard+, which enhances the margin between the representations of benign and malicious features through a carefully designed Dual-Centered Contrastive Loss (DCCLoss). Finally, we conduct extensive experiments on both CP-GuardBench and V2X-Sim, and demonstrate the superiority of CP-Guard+.

Zihan Wang, Rui Zhang, Hongwei Li et al.

Backdoor attacks pose a significant threat to Large Language Models (LLMs), where adversaries can embed hidden triggers to manipulate LLM's outputs. Most existing defense methods, primarily designed for classification tasks, are ineffective against the autoregressive nature and vast output space of LLMs, thereby suffering from poor performance and high latency. To address these limitations, we investigate the behavioral discrepancies between benign and backdoored LLMs in output space. We identify a critical phenomenon which we term sequence lock: a backdoored model generates the target sequence with abnormally high and consistent confidence compared to benign generation. Building on this insight, we propose ConfGuard, a lightweight and effective detection method that monitors a sliding window of token confidences to identify sequence lock. Extensive experiments demonstrate ConfGuard achieves a near 100\% true positive rate (TPR) and a negligible false positive rate (FPR) in the vast majority of cases. Crucially, the ConfGuard enables real-time detection almost without additional latency, making it a practical backdoor defense for real-world LLM deployments.

Shuai Yuan, Guowen Xu, Hongwei Li et al.

Traffic sign recognition (TSR) systems are crucial for autonomous driving but are vulnerable to backdoor attacks. Existing physical backdoor attacks either lack stealth, provide inflexible attack control, or ignore emerging Vision-Large-Language-Models (VLMs). In this paper, we introduce FIGhost, the first physical-world backdoor attack leveraging fluorescent ink as triggers. Fluorescent triggers are invisible under normal conditions and activated stealthily by ultraviolet light, providing superior stealthiness, flexibility, and untraceability. Inspired by real-world graffiti, we derive realistic trigger shapes and enhance their robustness via an interpolation-based fluorescence simulation algorithm. Furthermore, we develop an automated backdoor sample generation method to support three attack objectives. Extensive evaluations in the physical world demonstrate FIGhost's effectiveness against state-of-the-art detectors and VLMs, maintaining robustness under environmental variations and effectively evading existing defenses.

Zihan Wang, Hongwei Li, Rui Zhang et al.

In this paper, we present a new form of backdoor attack against Large Language Models (LLMs): lingual-backdoor attacks. The key novelty of lingual-backdoor attacks is that the language itself serves as the trigger to hijack the infected LLMs to generate inflammatory speech. They enable the precise targeting of a specific language-speaking group, exacerbating racial discrimination by malicious entities. We first implement a baseline lingual-backdoor attack, which is carried out by poisoning a set of training data for specific downstream tasks through translation into the trigger language. However, this baseline attack suffers from poor task generalization and is impractical in real-world settings. To address this challenge, we design BadLingual, a novel task-agnostic lingual-backdoor, capable of triggering any downstream tasks within the chat LLMs, regardless of the specific questions of these tasks. We design a new approach using PPL-constrained Greedy Coordinate Gradient-based Search (PGCG) based adversarial training to expand the decision boundary of lingual-backdoor, thereby enhancing the generalization ability of lingual-backdoor across various tasks. We perform extensive experiments to validate the effectiveness of our proposed attacks. Specifically, the baseline attack achieves an ASR of over 90% on the specified tasks. However, its ASR reaches only 37.61% across six tasks in the task-agnostic scenario. In contrast, BadLingual brings up to 37.35% improvement over the baseline. Our study sheds light on a new perspective of vulnerabilities in LLMs with multilingual capabilities and is expected to promote future research on the potential defenses to enhance the LLMs' robustness

Haonan An, Guang Hua, Zhengru Fang et al.

The intellectual property of deep image-to-image models can be protected by the so-called box-free watermarking. It uses an encoder and a decoder, respectively, to embed into and extract from the model's output images invisible copyright marks. Prior works have improved watermark robustness, focusing on the design of better watermark encoders. In this paper, we reveal an overlooked vulnerability of the unprotected watermark decoder which is jointly trained with the encoder and can be exploited to train a watermark removal network. To defend against such an attack, we propose the decoder gradient shield (DGS) as a protection layer in the decoder API to prevent gradient-based watermark removal with a closed-form solution. The fundamental idea is inspired by the classical adversarial attack, but is utilized for the first time as a defensive mechanism in the box-free model watermarking. We then demonstrate that DGS can reorient and rescale the gradient directions of watermarked queries and stop the watermark remover's training loss from converging to the level without DGS, while retaining decoder output image quality. Experimental results verify the effectiveness of proposed method. Code of paper will be made available upon acceptance.

Guanlin Li, Guowen Xu, Han Qiu et al.

Generative Adversarial Networks (GANs) have been widely used in various application scenarios. Since the production of a commercial GAN requires substantial computational and human resources, the copyright protection of GANs is urgently needed. This paper presents a novel fingerprinting scheme for the Intellectual Property (IP) protection of image-to-image GANs based on a trusted third party. We break through the stealthiness and robustness bottlenecks suffered by previous fingerprinting methods for classification models being naively transferred to GANs. Specifically, we innovatively construct a composite deep learning model from the target GAN and a classifier. Then we generate fingerprint samples from this composite model, and embed them in the classifier for effective ownership verification. This scheme inspires some concrete methodologies to practically protect the modern image-to-image translation GANs. Theoretical analysis proves that these methods can satisfy different security requirements necessary for IP protection. We also conduct extensive experiments to show that our solutions outperform existing strategies.

Shangwei Guo, Tianwei Zhang, Guowen Xu et al.

In this paper, we design Top-DP, a novel solution to optimize the differential privacy protection of decentralized image classification systems. The key insight of our solution is to leverage the unique features of decentralized communication topologies to reduce the noise scale and improve the model usability. (1) We enhance the DP-SGD algorithm with this topology-aware noise reduction strategy, and integrate the time-aware noise decay technique. (2) We design two novel learning protocols (synchronous and asynchronous) to protect systems with different network connectivities and topologies. We formally analyze and prove the DP requirement of our proposed solutions. Experimental evaluations demonstrate that our solution achieves a better trade-off between usability and privacy than prior works. To the best of our knowledge, this is the first DP optimization work from the perspective of network topologies.