检索结果-内蒙古大学图书馆

Securely Fine-tuning Pre-trained Encoders Against Adversarial Examples

学校读者我要写书评

暂无评论

Securely Fine-tuning Pre-trained Encoders Against Adversaria...

IEEE Symposium on Security and Privacy

作者： Ziqi Zhou Minghui Li Wei Liu Shengshan Hu Yechao Zhang Wei Wan Lulu Xue Leo Yu Zhang Dezhong Yao Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology School of Software Engineering Huazhong University of Science and Technology Hubei Engineering Research Center on Big Data Security Hubei Key Laboratory of Distributed System Security School of Cyber Science and Engineering Huazhong University of Science and Technology School of Information and Communication Technology Griffith University

ISBN: (数字)9798350331301

ISBN: (纸本)9798350331318

With the evolution of self-supervised learning, the pre-training paradigm has emerged as a predominant solution within the deep learning landscape. Model providers furnish pre-trained encoders designed to function as versatile feature extractors, enabling downstream users to harness the benefits of expansive models with minimal effort through fine-tuning. Nevertheless, recent works have exposed a vulnerability in pre-trained encoders, highlighting their susceptibility to downstream-agnostic adversarial examples (DAEs) meticulously crafted by attackers. The lingering question pertains to the feasibility of fortifying the robustness of downstream models against DAEs, particularly in scenarios where the pre-trained encoders are publicly accessible to the *** this paper, we initially delve into existing defensive mechanisms against adversarial examples within the pre-training paradigm. Our findings reveal that the failure of current defenses stems from the domain shift between pre-training data and downstream tasks, as well as the sensitivity of encoder parameters. In response to these challenges, we propose Genetic Evolution-Nurtured Adversarial Fine-tuning (Gen-AF), a two-stage adversarial fine-tuning approach aimed at enhancing the robustness of downstream models. Gen-AF employs a genetic-directed dual-track adversarial fine-tuning strategy in its first stage to effectively inherit the pre-trained encoder. This involves optimizing the pre-trained encoder and classifier separately while incorporating genetic regularization to preserve the model’s topology. In the second stage, Gen-AF assesses the robust sensitivity of each layer and creates a dictionary, based on which the top-k robust redundant layers are selected with the remaining layers held fixed. Upon this foundation, we conduct evolutionary adaptability fine-tuning to further enhance the model’s generalizability. Our extensive experiments, conducted across ten self-supervised training methods and six d

关键词： Training Adaptation models Sensitivity Accuracy Self-supervised learning Genetics Feature extraction

MISA: Unveiling the Vulnerabilities in Split Federated Learning

学校读者我要写书评

暂无评论

MISA: Unveiling the Vulnerabilities in Split Federated Learn...

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Wei Wan Yuxuan Ning Shengshan Hu Lulu Xue Minghui Li Leo Yu Zhang Hai Jin School of Cyber Science and Engineering Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Computer Science and Technology Huazhong University of Science and Technology School of Software Engineering Huazhong University of Science and Technology School of Information and Communication Technology Griffith University Cluster and Grid Computing Lab

Federated learning (FL) and split learning (SL) are prevailing distributed paradigms in recent years. They both enable shared global model training while keeping data localized on users’ devices. The former excels in parallel execution capabilities, while the latter enjoys low dependence on edge computing resources and strong privacy protection. Split federated learning (SFL) combines the strengths of both FL and SL, making it one of the most popular distributed architectures. Furthermore, a recent study has claimed that SFL exhibits robustness against poisoning attacks, with a fivefold improvement compared to FL in terms of *** this paper, we present a novel poisoning attack known as $\color{Fuchsia} {{\text{MISA}}}$. It poisons both the top and bottom models, causing a misalignment in the global model, ultimately leading to a drastic accuracy collapse. This attack unveils the vulnerabilities in SFL, challenging the conventional belief that SFL is robust against poisoning attacks. Extensive experiments demonstrate that our proposed MISA poses a significant threat to the availability of SFL, underscoring the imperative for academia and industry to accord this matter due attention.

关键词：

DarkSAM: Fooling Segment Anything Model to Segment Nothing

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhou, Ziqi Song, Yufei Li, Minghui Hu, Shengshan Wang, Xianlong Zhang, Leo Yu Yao, Dezhong Jin, Hai National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Cluster and Grid Computing Lab China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia

Segment Anything Model (SAM) has recently gained much attention for its outstanding generalization to unseen data and tasks. Despite its promising prospect, the vulnerabilities of SAM, especially to universal adversarial perturbation (UAP) have not been thoroughly investigated yet. In this paper, we propose DarkSAM, the first prompt-free universal attack framework against SAM, including a semantic decoupling-based spatial attack and a texture distortion-based frequency attack. We first divide the output of SAM into foreground and background. Then, we design a shadow target strategy to obtain the semantic blueprint of the image as the attack target. DarkSAM is dedicated to fooling SAM by extracting and destroying crucial object features from images in both spatial and frequency domains. In the spatial domain, we disrupt the semantics of both the foreground and background in the image to confuse SAM. In the frequency domain, we further enhance the attack effectiveness by distorting the high-frequency components (i.e., texture information) of the image. Consequently, with a single UAP, DarkSAM renders SAM incapable of segmenting objects across diverse images with varying prompts. Experimental results on four datasets for SAM and its two variant models demonstrate the powerful attack capability and transferability of DarkSAM. Our codes are available at: https://***/CGCL-codes/DarkSAM. Copyright © 2024, The Authors. All rights reserved.

关键词： Frequency domain analysis

Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency

学校读者我要写书评

暂无评论

Detecting Backdoors During the Inference Stage Based on Corr...

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Xiaogeng Liu Minghui Li Haoyu Wang Shengshan Hu Dengpan Ye Hai Jin Libing Wu Chaowei Xiao School of Cyber Science and Engineering Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Software Engineering Huazhong University of Science and Technology School of Cyber Science and Engineering Wuhan University School of Computer Science and Technology Huazhong University of Science and Technology Cluster and Grid Computing Lab Arizona State University

Deep neural networks are proven to be vulnerable to backdoor attacks. Detecting the trigger samples during the inference stage, i.e., the test-time trigger sample detection, can prevent the backdoor from being triggered. However, existing detection methods often require the defenders to have high accessibility to victim models, extra clean data, or knowledge about the appearance of backdoor triggers, limiting their practicality. In this paper, we propose the test-time corruption robustness consistency evaluation (TeCo) 1 1 https://***/CGCL-codes/TeCo, a novel test-time trigger sample detection method that only needs the hard-label outputs of the victim models without any extra information. Our journey begins with the intriguing observation that the backdoor-infected models have similar performance across different image corruptions for the clean images, but perform discrepantly for the trigger samples. Based on this phenomenon, we design TeCo to evaluate test-time robustness consistency by calculating the deviation of severity that leads to predictions' transition across different corruptions. Extensive experiments demonstrate that compared with state-of-the-art defenses, which even require either certain information about the trigger types or accessibility of clean data, TeCo outperforms them on different backdoor attacks, datasets, and model architectures, enjoying a higher AUROC by 10% and 5 times of stability.

关键词：

Breaking Barriers in Physical-World Adversarial Examples: Improving Robustness and Transferability via Robust Feature

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Yichen Chou, Yuxuan Zhou, Ziqi Zhang, Hangtao Wan, Wei Hu, Shengshan Li, Minghui National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Cluster and Grid Computing Lab China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China School of School of Software Engineering Huazhong University of Science and Technology China

As deep neural networks (DNNs) are widely applied in the physical world, many researches are focusing on physical-world adversarial examples (PAEs), which introduce perturbations to inputs and cause the model’s incorrect outputs. However, existing PAEs face two challenges: unsatisfactory attack performance (i.e., poor transferability and insufficient robustness to environment conditions), and difficulty in balancing attack effectiveness with stealthiness, where better attack effectiveness often makes PAEs more perceptible. In this paper, we explore a novel perturbation-based method to overcome the challenges. For the first challenge, we introduce a strategy Deceptive RF injection based on robust features (RFs) that are predictive, robust to perturbations, and consistent across different models. Specifically, it improves the transferability and robustness of PAEs by covering RFs of other classes onto the predictive features in clean images. For the second challenge, we introduce another strategy Adversarial Semantic Pattern Minimization, which removes most perturbations and retains only essential adversarial patterns in AEs. Based on the two strategies, we design our method Robust Feature Coverage Attack (RFCoA), comprising Robust Feature Disentanglement and Adversarial Feature Fusion. In the first stage, we extract target class RFs in feature space. In the second stage, we use attention-based feature fusion to overlay these RFs onto predictive features of clean images and remove unnecessary perturbations. Experiments show our method’s superior transferability, robustness, and stealthiness compared to existing state-of-the-art methods. Additionally, our method’s effectiveness can extend to Large Vision-Language Models (LVLMs), indicating its potential applicability to more complex tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep neural networks

BADROBOT: JAILBREAKING EMBODIED LLMS IN THE PHYSICAL WORLD

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Hangtao Zhu, Chenyu Wang, Xianlong Zhou, Ziqi Yin, Changgan Li, Minghui Xue, Lulu Wang, Yichen Hu, Shengshan Liu, Aishan Guo, Peijin Zhang, Leo Yu National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Cluster and Grid Computing Lab China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China Beihang University China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia

Embodied AI represents systems where AI is integrated into physical entities. Large Language Model (LLM), which exhibits powerful language understanding abilities, has been extensively employed in embodied AI by facilitating sophisticated task planning. However, a critical safety issue remains overlooked: could these embodied LLMs perpetrate harmful behaviors? In response, we introduce BADROBOT, a novel attack paradigm aiming to make embodied LLMs violate safety and ethical constraints through typical voice-based user-system interactions. Specifically, three vulnerabilities are exploited to achieve this type of attack: (i) manipulation of LLMs within robotic systems, (ii) misalignment between linguistic outputs and physical actions, and (iii) unintentional hazardous behaviors caused by world knowledge’s flaws. Furthermore, we construct a benchmark of various malicious physical action queries to evaluate BADROBOT’s attack performance. Based on this benchmark, extensive experiments against existing prominent embodied LLM frameworks (e.g., Voxposer, Code as Policies, and ProgPrompt) demonstrate the effectiveness of our BADROBOT. Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking

On the Effectiveness of Function-Level Vulnerability Detectors for Inter-Procedural Vulnerabilities

学校读者我要写书评

暂无评论

On the Effectiveness of Function-Level Vulnerability Detecto...

International Conference on Software Engineering (ICSE)

作者： Zhen Li Ning Wang Deqing Zou Yating Li Ruqian Zhang Shouhuai Xu Chao Zhang Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security Cluster and Grid Computing Lab School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China Jin YinHu Laboratory Wuhan China Department of Computer Science University of Colorado Colorado Springs Colorado Springs Colorado USA Institute for Network Sciences and Cyberspace Tsinghua University Beijing China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9798400702174

ISBN: (纸本)9798350382143

Software vulnerabilities are a major cyber threat and it is important to detect them. One important approach to detecting vulnerabilities is to use deep learning while treating a program function as a whole, known as function-level vulnerability detectors. However, the limitation of this approach is not understood. In this paper, we investigate its limitation in detecting one class of vulnerabilities known as inter-procedural vulnerabilities, where the to-be-patched statements and the vulnerability-triggering statements belong to different functions. For this purpose, we create the first Inter -Procedural Vulnerability Dataset (InterPVD) based on C/C++ open-source software, and we propose a tool dubbed VulTrigger for identifying vulnerability-triggering statements across functions. Experimental results show that VulTrigger can effectively identify vulnerability-triggering statements and inter-procedural vulnerabilities. Our findings include: (i) inter-procedural vulnerabilities are prevalent with an average of 2.8 inter-procedural layers; and (ii) function-level vulner-ability detectors are much less effective in detecting to-be-patched functions of inter-procedural vulnerabilities than detecting their counterparts of intra-procedural vulnerabilities.

关键词： Deep learning Detectors Open source software Software engineering

On the Effectiveness of Function-Level Vulnerability Detectors for Inter-Procedural Vulnerabilities

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Zhen Wang, Ning Zou, Deqing Li, Yating Zhang, Ruqian Xu, Shouhuai Zhang, Chao Jin, Hai School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China Department of Computer Science University of Colorado Colorado Springs Colorado SpringsCO United States Institute for Network Sciences and Cyberspace Tsinghua University Beijing China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security Cluster and Grid Computing Lab China JinYinHu Laboratory Wuhan China

Software vulnerabilities are a major cyber threat and it is important to detect them. One important approach to detecting vulnerabilities is to use deep learning while treating a program function as a whole, known as function-level vulnerability detectors. However, the limitation of this approach is not understood. In this paper, we investigate its limitation in detecting one class of vulnerabilities known as inter-procedural vulnerabilities, where the to-be-patched statements and the vulnerability-triggering statements belong to different functions. For this purpose, we create the first Inter-Procedural Vulnerability Dataset (InterPVD) based on C/C++ open-source software, and we propose a tool dubbed VulTrigger for identifying vulnerability-triggering statements across functions. Experimental results show that VulTrigger can effectively identify vulnerability-triggering statements and inter-procedural vulnerabilities. Our findings include: (i) inter-procedural vulnerabilities are prevalent with an average of 2.8 inter-procedural layers;and (ii) function-level vulnerability detectors are much less effective in detecting to-be-patched functions of inter-procedural vulnerabilities than detecting their counterparts of intra-procedural vulnerabilities. Copyright © 2024, The Authors. All rights reserved.

关键词： Open source software

Generalization-Enhanced Code Vulnerability Detection via Multi-Task Instruction Fine-Tuning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Du, Xiaohu Wen, Ming Zhu, Jiahao Xie, Zifan Ji, Bin Liu, Huijun Shi, Xuanhua Jin, Hai School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China College of Computer National University of Defense Technology China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab HUST Wuhan430074 China Hubei Engineering Research Center on Big Data Security Hubei Key Laboratory of Distributed System Security HUST Wuhan430074 China JinYinHu Laboratory Wuhan430077 China Cluster and Grid Computing Lab HUST Wuhan430074 China

Code Pre-trained Models (CodePTMs) based vulnerability detection have achieved promising results over recent years. However, these models struggle to generalize as they typically learn superficial mapping from source code to labels instead of understanding the root causes of code vulnerabilities, resulting in poor performance in real-world scenarios beyond the training instances. To tackle this challenge, we introduce VulLLM, a novel framework that integrates multi-task learning with Large Language Models (LLMs) to effectively mine deep-seated vulnerability features. Specifically, we construct two auxiliary tasks beyond the vulnerability detection task. First, we utilize the vulnerability patches to construct a vulnerability localization task. Second, based on the vulnerability features extracted from patches, we leverage GPT-4 to construct a vulnerability interpretation task. VulLLM innovatively augments vulnerability classification by leveraging generative LLMs to understand complex vulnerability patterns, thus compelling the model to capture the root causes of vulnerabilities rather than overfitting to spurious features of a single task. The experiments conducted on six large datasets demonstrate that VulLLM surpasses seven state-of-the-art models in terms of effectiveness, generalization, and robustness. © 2024, CC BY.

关键词： Large datasets