检索结果-内蒙古大学图书馆

IEEE International Conference on Multimedia and Expo (ICME)

作者： Yaxi Chen Ruimin Hu Danni Xu Zheng Wang Linbo Luo Dengshi Li National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan China Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan China School of Computing the National University of Singapore Singapore School of Cyber Engineering Xidian University Xi’an China School of Artificial Intelligence Jianghan University Wuhan China

Hidden following is following behavior with special intentions, and detecting hidden following behavior can prevent many criminal activities in advance. The previous method uses gaze and spacing behaviors to distinguish hidden followers from normal pedestrians. However, they express gaze behaviors in a coarse-grained way with binary values, making it difficult to accurately depict the gaze state of pedestrians. To this end, we propose the Refined Hidden Follower Detection (RHFD) model by choosing a suitable mapping function based on the principle that the closer the gaze direction is to someone, the more likely it is to gaze at someone, which converts the gaze direction into a continuous estimated gaze state representing the complex and variable gaze behavior of pedestrians. Simultaneously, we introduce variations in the magnitude and direction of pedestrian velocity to refine the representation of pedestrian walking states. Experimental results on the surveillance dataset show that RHFD outperforms state-of-the-art methods.

关键词：

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

An efficient privacy-preserving compressive data gathering scheme in WSNs 1

引用

15th International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2015

作者： Xie, Kun Ning, Xueping Wang, Xin Wen, Jigang Liu, Xiaoxiao He, Shiming Zhang, Daqiang College of Computer Science and Electronics Engineering Hunan University Changsha410082 China The State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommmunications Beijing100876 China Department of Electrical and Computer Engineering State University of New York at Stony Brook New York11790 United States Institute of Computing Technology Chinese Academy of Sciences Beijing100080 China State Grid HuNan Electric Power Company Research Insitute Changsha410000 China School of Computer and Communication Engineering Changsha University of Science and Technology Changsha410114 China School of Software Engineering Tongji University Shanghai201804 China

ISBN: (数字)9783319271194

ISBN: (纸本)9783319271187

Due to the strict energy limitation and the common vulnerability of WSNs, providing efficient and security data gathering in WSNs becomes an essential problem. Compressive data gathering, which is based on the recent breakthroughs in compressive sensing theory, has been proposed as a viable approach for data gathering in WSNs at low communication overhead. Nevertheless, compressive data gathering is susceptible to various attacks due to the open wireless medium. To thwart traffic analysis/flow tracing and realize privacy preservation, this paper proposes a novel Efficient Privacy-Preserving Compressive Data Gathering Scheme which exploits homomorphic encryption functions in compressive data gathering. With homomorphic encryption on the compressive sensing encoded sensory reading messages, the proposed scheme offers two significant privacy-preserving features, message flow untraceability and message content confidentiality, for efficiently thwarting the traffic analysis attacks. Extensive performance evaluations and security analysis demonstrate the validity and efficiency of the proposed scheme. © Springer International Publishing Switzerland 2015.

关键词： Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Requirement-oriented privacy protection analysis architecture in cloud computing

引用

Journal of communications 2015年第1期10卷 55-63页

作者： Ke, Changbo Wang, Ruchuan Xiao, Fu Huang, Zhiqiu School of Computer Sci. and Tech./School of Software Nanjing Univ. of Posts and Telecom Nanjing210023 China Jiangsu High Tech Research Key Laboratory for Wireless Sensor Networks NanjingJiangsu210003 China College of computer Sci. and Tech Nanjing Univ. of Aeronautics and Astronautics NanjingJiangsu210016 China Key Lab of Broadband Wireless Communication and Sensor Network Tech Nanjing University of Posts and Telecom Ministry of Education Jiangsu Province NanjingJiangsu210003 China

As a new software paradigm, cloud computing provides services dynamically according to user requirements. However, it is difficult to control personal privacy information because of the opening, virtualization, multi-tenancy and service outsourcing characters. Therefore, how to protect user privacy information has become a research focus. In this paper, we propose requirement-oriented privacy protection theory analysis architecture and implementation platform. Firstly, the theory analysis architecture is depicted as layers, and we analyze the function and key technologies of every layer. Secondly, we address the privacy property description method with ontology and description logic, and then analyze the theory modules of privacy items conflict checking layer, privacy policy negotiation layer and privacy agreement forensics layer. Thirdly, according to theory architecture, we design the implementation platform of requirement-oriented privacy protection, and discuss the function and workflow. In the end, we conclude and point out the future work. © 2015 Engineering and Technology Publishing.

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

Securely Fine-tuning Pre-trained Encoders Against Adversarial Examples

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

引用

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

MISA: Unveiling the Vulnerabilities in Split Federated Learning

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

引用

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：

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

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

Socially Beneficial Metaverse: Framework, Technologies, Applications, and Challenges

arXiv

引用

arXiv 2023年

作者： Xu, Xiaolong Zhou, Xuanhong Bilal, Muhammad Zeadally, Sherali Crowcroft, Jon Qi, Lianyong Xue, Shengjun Nanjing University of Information Science and Technology Nanjing China School of Software Nanjing University of Information Science and Technology Nanjing China School of Computing and Communications Lancaster University Lancaster United Kingdom College of Communication and Information University of Kentucky Lexington United States Department of Computer Science and Technology University of Cambridge Cambridge United Kingdom State Key Laboratory for Novel Software Technology Nanjing University China School of Computer Science and Technology Silicon Lake College Suzhou China

In recent years, the maturation of emerging technologies such as Virtual Reality, Digital Twin,s and Blockchain has accelerated the realization of the metaverse. As a virtual world independent of the real world, the metaverse will provide users with a variety of virtual activities which bring great convenience to society. In addition, the metaverse can facilitate digital twins, which offers transformative possibilities for the industry. Thus, the metaverse has attracted the attention of the industry, and a huge amount of capital is about to be invested. However, the development of the metaverse is still in its infancy and little research has been undertaken so far. We describe the development of the metaverse. Next, we introduce the architecture of the socially beneficial metaverse (SB-Metaverse) and we focus on the technologies that support the operation of SB-Metaverse. In addition, we also present the applications of SB-Metaverse. Finally, we discuss several challenges faced by SB-Metaverse which must be addressed in the *** Codes 68U01, 68M11, 68U35 © 2023, CC BY.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Method for labor scheduling in multi-skill call centers

引用

Shanghai Jiaotong Daxue Xuebao/Journal of Shanghai Jiaotong University 2007年第7期41卷 1169-1175页

作者： Wu, Jia-Ji Huang, Liu-Sheng Wu, Jun-Min Wang, Pei Yang, Zhou-Wang Dept. of Computer Science Univ. of Science and Technology of China Hefei 230027 China Anhui Province Key Lab. of Software in Computing and Communication Hefei 230027 China Dept. of Mathematics Univ. of Science and Technology of China Hefei 230026 China

This paper extended the set-covering model for single-skill call centers, proposed by Dantzig, to handle multi-skill cases. First is solves the staffing level of each period for each skill, using the classical formulas in queueing system theory;second, it decomposes a multi-skill agent to a combination of single-skill agents in every period;and then it models the shift scheduling problem in a linear programming framework. The new model makes the most use of the flexibility of multi-skill agents. The experiments show that by the proposed model, solutions of high performance can be found stably in a short period of time, which are acceptable in practice. The solutions provide informative guidance for overall planning of the call center. The solutions also provide a new way to deal with the call routing problem.

关键词： Information services

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：