检索结果-内蒙古大学图书馆

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

来源：评论

学校读者我要写书评

暂无评论

DarkSAM: Fooling Segment Anything Model to Segment Nothing

arXiv

引用

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

来源：评论

学校读者我要写书评

暂无评论

Understanding the Robustness of 3D Object Detection with Bird’s-Eye-View Representations in Autonomous Driving

arXiv

引用

arXiv 2023年

作者： Zhu, Zijian Zhang, Yichi Chen, Hai Dong, Yinpeng Zhao, Shu Ding, Wenbo Zhong, Jiachen Zheng, Shibao Institute of Image Communication and Network Engineering Shanghai Jiao Tong University China Dept. of Comp. Sci. and Tech. Institute for AI THBI Lab BNRist Center Tsinghua University China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education School of Computer Science and Technology Anhui University Information Materials and Intelligent Sensing Laboratory of Anhui Province China SAIC Motor AI Lab China Zhongguancun Laboratory China

3D object detection is an essential perception task in autonomous driving to understand the environments. The Bird’s-Eye-View (BEV) representations have significantly improved the performance of 3D detectors with camera inputs on popular benchmarks. However, there still lacks a systematic understanding of the robustness of these vision-dependent BEV models, which is closely related to the safety of autonomous driving systems. In this paper, we evaluate the natural and adversarial robustness of various representative models under extensive settings, to fully understand their behaviors influenced by explicit BEV features compared with those without BEV. In addition to the classic settings, we propose a 3D consistent patch attack by applying adversarial patches in the 3D space to guarantee the spatiotemporal consistency, which is more realistic for the scenario of autonomous driving. With substantial experiments, we draw several findings: 1) BEV models tend to be more stable than previous methods under different natural conditions and common corruptions due to the expressive spatial representations;2) BEV models are more vulnerable to adversarial noises, mainly caused by the redundant BEV features;3) Camera-LiDAR fusion models have superior performance under different settings with multi-modal inputs, but BEV fusion model is still vulnerable to adversarial noises of both point cloud and image. These findings alert the safety issue in the applications of BEV detectors and could facilitate the development of more robust models. Code available at https: //***/zzj403/BEV_Robust. Copyright © 2023, The Authors. All rights reserved.

关键词： Birds

来源：评论

学校读者我要写书评

暂无评论

Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferability

Why Does Little Robustness Help? A Further Step Towards Unde...

引用

IEEE Symposium on Security and Privacy

作者： Yechao Zhang Shengshan Hu Leo Yu Zhang Junyu Shi Minghui Li Xiaogeng Liu Wei Wan Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab 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 School of Software Engineering Huazhong University of Science and Technology Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology

ISBN: (数字)9798350331301

ISBN: (纸本)9798350331318

Adversarial examples for deep neural networks (DNNs) are transferable: examples that successfully fool one white-box surrogate model can also deceive other black-box models with different architectures. Although a bunch of empirical studies have provided guidance on generating highly transferable adversarial examples, many of these findings fail to be well explained and even lead to confusing or inconsistent advice for practical *** this paper, we take a further step towards understanding adversarial transferability, with a particular focus on surrogate aspects. Starting from the intriguing "little robustness" phenomenon, where models adversarially trained with mildly perturbed adversarial samples can serve as better surrogates for transfer attacks, we attribute it to a trade-off between two dominant factors: model smoothness and gradient similarity. Our research focuses on their joint effects on transferability, rather than demonstrating the separate relationships alone. Through a combination of theoretical and empirical analyses, we hypothesize that the data distribution shift induced by off-manifold samples in adversarial training is the reason that impairs gradient *** on these insights, we further explore the impacts of prevalent data augmentation and gradient regularization on transferability and analyze how the trade-off manifests in various training methods, thus building a comprehensive blueprint for the regulation mechanisms behind transferability. Finally, we provide a general route for constructing superior surrogates to boost transferability, which optimizes both model smoothness and gradient similarity simultaneously, e.g., the combination of input gradient regularization and sharpness-aware minimization (SAM), validated by extensive experiments. In summary, we call for attention to the united impacts of these two factors for launching effective transfer attacks, rather than optimizing one while ignoring the other, and emphasize the

关键词： Training Privacy Buildings Closed box Minimization Data augmentation Robustness

来源：评论

学校读者我要写书评

暂无评论

Rank-one Projections with Adaptive Margins for Face Recognition

Rank-one Projections with Adaptive Margins for Face Recognit...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Dong Xu S. Lin Shuicheng Yan Xiaoou Tang Department of Electrical Engineering Columbia University USA MOE-Microsoft Key Laboratory of Multimedia Computing and Communication & Department of EEIS University of Science and Technology Hefei Anhui China Microsoft Research Asia Beijing China Department of Information Engineering Chinese University of Hong Kong Hong Kong China Beckman Institute University of Illinois Urbana-Champaign Champaign USA

In supervised dimensionality reduction, tensor representations of images have recently been employed to enhance classification of high-dimensional data with small training sets. To handle tensor data, this approach has been formulated with tight restrictions on projection directions that, along with convergence issues and the assumption of Gaussian distributed class data, limits its face recognition performance. To overcome these problems, we propose a method of rank-one projections with adaptive margins (RPAM) that gives a provably convergent solution for tensor data over a more general class of projections, while accounting for margins between samples of different classes. In contrast to previous margin based works which determine margin sample pairs within the original high dimensional space, RPAM instead aims to maximize the margins defined in the expected lower dimensional feature subspace by progressive margin refinement after each rank-one projection. In addition to handling tensor data, vector-based variants of RPAM are presented for linear mappings and for nonlinear mappings using kernel tricks. Comprehensive experimental results demonstrate that RPAM brings significant improvement in face recognition over previous subspace learning techniques.

关键词： Face recognition Tensile stress Linear discriminant analysis Asia Computer vision Pattern recognition Scattering Laboratories Multimedia computing Data engineering

来源：评论

学校读者我要写书评

暂无评论

BADROBOT: JAILBREAKING EMBODIED LLMS IN THE PHYSICAL WORLD

arXiv

引用

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

来源：评论

学校读者我要写书评

暂无评论

An Optimized Hierarchical Classifier for Pedestrian Detection

An Optimized Hierarchical Classifier for Pedestrian Detectio...

引用

7th World Congress on Intelligent Control and Automation (WCICA 2008), vol.3

作者： Yanwu Xu Xianbin Cao Hong Qiao Department of Computer Science and Technology University of Science and Technology Hefei China Anhui Province Key Laboratory of Software Computing and Communication Hefei China Institute of Automation Chinese Academy and Sciences Beijing China

Classification is an essential technology in Pedestrian Detection System (PDS). Until now, single-classifier and basic cascaded classifier had been widely used in PDS;however, most of them can hardly satisfy the 3 requirements at the same time: high detection speed, high detection rate and low false positive rate. In this paper, we proposed an optimized hierarchical classifier which can satisfy the 3 requirements. The proposed method adopted Corse-to-fine and Early-rejection principles to achieve global high performance. It consists of two hierarchies, the first one is used to quickly reject non-pedestrian objects and select out only a few candidates;the second one makes further verification to these candidates. Furthermore, each hierarchy was optimized with statistical models basing on experiments;and each hierarchy is a treelike classifier which has specific optimization demands. At last, an overall performance evaluation standard is proposed, and the experimental results showed that the proposed classifier had better overall performance.

关键词： Pedestrian detection Hierarchical classifier AdaBoost

来源：评论

学校读者我要写书评

暂无评论

Discriminant analysis with tensor representation

Discriminant analysis with tensor representation

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Shuicheng Yan Dong Xu Qiang Yang Lei Zhang Xiaoou Tang Hong-Jiang Zhang Department of Information Engineering Chinese University of Hong Kong Sha Tin Hong Kong China MOE-Microsoft Key Laboratory of Multimedia Computing and Communication & Department of EEIS University of Science and Technology Hefei Anhui China Department of Computer Science Hong Kong University of Science and Technology Hong Kong China Microsoft Research Asia Beijing China

ISBN: (纸本)0769523722

In this paper, we present a novel approach to solving the supervised dimensionality reduction problem by encoding an image object as a general tensor of 2nd or higher order. First, we propose a discriminant tensor criterion (DTC), whereby multiple interrelated lower-dimensional discriminative subspaces are derived for feature selection. Then, a novel approach called k-mode cluster-based discriminant analysis is presented to iteratively learn these subspaces by unfolding the tensor along different tensor dimensions. We call this algorithm discriminant analysis with tensor representation (DATER), which has the following characteristics: 1) multiple interrelated subspaces can collaborate to discriminate different classes; 2) for classification problems involving higher-order tensors, the DATER algorithm can avoid the curse of dimensionality dilemma and overcome the small sample size problem; and 3) the computational cost in the learning stage is reduced to a large extent owing to the reduced data dimensions in generalized eigenvalue decomposition. We provide extensive experiments by encoding face images as 2nd or 3rd order tensors to demonstrate that the proposed DATER algorithm based on higher order tensors has the potential to outperform the traditional subspace learning algorithms, especially in the small sample size cases.

关键词： Tensile stress Iterative algorithms Linear discriminant analysis Scattering Asia Image coding Clustering algorithms Algorithm design and analysis Principal component analysis Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Cellular signal transduction network simulation based on microscopic agent model

引用

Xitong Fangzhen Xuebao / Journal of System Simulation 2008年第17期20卷 4703-4707页

作者： Shao, Chen-Xi Deng, Hong-Li Yang, Ming Wang, Zi-Cai Department of Computer Science and Technology University of Science and Technology of China Hefei 230027 China Control and Simulation Center Harbin Institute of Technology Harbin 150001 China Anhui Province Key Laboratory of Software in Computing and Communication Hefei 230027 China

A hierarchical MAS (multi-agent system) based on a multi-level discrete space and microscopic agent model for signal transduction network modeling and simulation was proposed. The space can effectively represent the heterogeneous cellular space, and is adaptable for systemic expansion. Moreover, the different deformations of one molecular species are packed in one mesoscopic molecule-agent, so that the global complexity is handled by the local state-space, reducing the external communications and computational complexity. The results from simulating two feedback models of MAPK (Mitogen-Activated Protein Kinase) pathway are similar to those of chemical kinetic model, showing the validity of this method.

关键词： Agent Cellular signal transduction Complex system Discrete space Microscopic level

来源：评论

学校读者我要写书评

暂无评论

Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferability

arXiv

引用

arXiv 2023年

作者： Zhang, Yechao Hu, Shengshan Zhang, Leo Yu Shi, Junyu Li, Minghui Liu, Xiaogeng Wan, Wei Jin, Hai 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 School of Computer Science and Technology Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security China Hubei Engineering Research Center on Big Data Security China Cluster and Grid Computing Lab

Adversarial examples for deep neural networks (DNNs) have been shown to be transferable: examples that successfully fool one white-box surrogate model can also deceive other black-box models with different architectures. Although a bunch of empirical studies have provided guidance on generating highly transferable adversarial examples, many of these findings fail to be well explained and even lead to confusing or inconsistent advice for practical use. In this paper, we take a further step towards understanding adversarial transferability, with a particular focus on surrogate aspects. Starting from the intriguing "little robustness" phenomenon, where models adversarially trained with mildly perturbed adversarial samples can serve as better surrogates for transfer attacks, we attribute it to a trade-off between two dominant factors: model smoothness and gradient similarity. Our research focuses on their joint effects on transferability, rather than demonstrating the separate relationships alone. Through a combination of theoretical and empirical analyses, we hypothesize that the data distribution shift induced by off-manifold samples in adversarial training is the reason that impairs gradient similarity. Building on these insights, we further explore the impacts of prevalent data augmentation and gradient regularization on transferability and analyze how the trade-off manifest in various training methods, thus building a comprehensive blueprint for the regulation mechanisms behind transferability. Finally, we provide a general route for constructing superior surrogates to boost transferability, which optimizes both model smoothness and gradient similarity simultaneously, e.g., the combination of input gradient regularization and sharpness-aware minimization (SAM), validated by extensive experiments. In summary, we call for attention to the united impacts of these two factors for launching effective transfer attacks, rather than optimizing one while ignoring the other,

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：