检索结果-内蒙古大学图书馆

IEEE International Conference on Trust, security and Privacy in Computing and Communications (TrustCom)

作者： Junyu Shi Wei Wan Shengshan Hu Jianrong Lu Leo Yu Zhang 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 Engineering Research Center on Big Data Security School of Information Technology Deakin University

Recently emerged federated learning (FL) is an attractive distributed learning framework in which numerous wireless end-user devices can train a global model with the data remained autochthonous. Compared with the traditional machine learning framework that collects user data for centralized storage, which brings huge communication burden and concerns about data privacy, this approach can not only save the network bandwidth but also protect the data privacy. Despite the promising prospect, Byzantine attack, an intractable threat in conventional distributed network, is discovered to be rather efficacious against FL as well. In this paper, we conduct a comprehensive investigation of the state-of-the-art strategies for defending against Byzantine attacks in FL. We first provide a taxonomy for the existing defense solutions according to the techniques they used, followed by an across-the-board comparison and discussion. Then we propose a new Byzantine attack method called weight attack to defeat those defense schemes, and conduct experiments to demonstrate its threat. The results show that existing defense solutions, although abundant, are still far from fully protecting FL. Finally, we indicate possible countermeasures for weight attack, and highlight several challenges and future research directions for mitigating Byzantine attacks in FL.

关键词： Wireless communication Training Privacy data privacy Federated learning Distance learning Taxonomy

来源：评论

学校读者我要写书评

暂无评论

A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trends

arXiv

引用

arXiv 2024年

作者： Liu, Daizong Yang, Mingyu Qu, Xiaoye Zhou, Pan Cheng, Yu Hu, Wei Wangxuan Institute of Computer Technology Peking University No. 128 Zhongguancun North Street Beijing China The Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China The Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong

With the significant development of large models in recent years, Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities across a wide range of multimodal understanding and reasoning tasks. Compared to traditional Large Language Models (LLMs), LVLMs present great potential and challenges due to its closer proximity to the multi-resource real-world applications and the complexity of multi-modal processing. However, the vulnerability of LVLMs is relatively underexplored, posing potential security risks in daily usage. In this paper, we provide a comprehensive review of the various forms of existing LVLM attacks. Specifically, we first introduce the background of attacks targeting LVLMs, including the attack preliminary, attack challenges, and attack resources. Then, we systematically review the development of LVLM attack methods, such as adversarial attacks that manipulate model outputs, jailbreak attacks that exploit model vulnerabilities for unauthorized actions, prompt injection attacks that engineer the prompt type and pattern, and data poisoning that affects model training. Finally, we discuss promising research directions in the future. We believe that our survey provides insights into the current landscape of LVLM vulnerabilities, inspiring more researchers to explore and mitigate potential safety issues in LVLM developments. The latest papers on LVLM attacks are continuously collected in https://***/liudaizong/Awesome-LVLM-Attack. Copyright © 2024, The Authors. All rights reserved.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Quantum partial least squares regression algorithm for multiple correlation problem

引用

Chinese Physics B 2022年第3期31卷 177-186页

作者： Yan-Yan Hou Jian Li Xiu-Bo Chen Yuan Tian School of Artificial Intelligence Beijing University of Post and TelecommunicationsBeijing 100876China College of Information Science and Engineering Zaozhuang UniversityZaozhuang 277160China Information Security Center State Key Laboratory of Networking and Switching TechnologyBeijing University of Post and TelecommunicationsBeijing 100876China GuiZhou University Guizhou Provincial Key Laboratory of Public Big DataGuiyang 550025China

Partial least squares(PLS) regression is an important linear regression method that efficiently addresses the multiple correlation problem by combining principal component analysis and multiple regression. In this paper, we present a quantum partial least squares(QPLS) regression algorithm. To solve the high time complexity of the PLS regression, we design a quantum eigenvector search method to speed up principal components and regression parameters construction. Meanwhile, we give a density matrix product method to avoid multiple access to quantum random access memory(QRAM)during building residual matrices. The time and space complexities of the QPLS regression are logarithmic in the independent variable dimension n, the dependent variable dimension w, and the number of variables m. This algorithm achieves exponential speed-ups over the PLS regression on n, m, and w. In addition, the QPLS regression inspires us to explore more potential quantum machine learning applications in future works.

关键词： quantum machine learning partial least squares regression eigenvalue decomposition

来源：评论

学校读者我要写书评

暂无评论

Network Situation Awareness Model Based on Incomplete Information Game 5th

Network Situation Awareness Model Based on Incomplete Inform...

引用

5th International Conference on security and Privacy in New Computing Environments, SPNCE 2022

作者： Zhang, Hongbin Yin, Yan Zhao, Dongmei Liu, Bin Wang, Yanxia Liu, Zhen School of Information Science and Engineering Hebei University of Science and Technology Shijiazhuang050000 China Hebei Key Laboratory of Network and Information Security Hebei Normal University Hebei Shijiazhuang050024 China School of Economics and Management Hebei University of Science and Technology Shijiazhuang050000 China Research Center of Big Data and Social Computing Hebei University of Science and Technology Shijiazhuang050000 China Hebei Geological Workers’ University Shijiazhuang050081 China

ISBN: (纸本)9783031306228

Game theory has been widely used in network security situational awareness. However, most of the currently proposed game-based offensive and defensive situational awareness methods are for traffic data, and there are fewer models or methods for analysis using vulnerability data. To overcome these issues, this paper proposes collecting periodic security vulnerability information in the network and utilizing the change in vulnerability status to achieve network security situational awareness. At this time, a network attack and defense game model based on incomplete information is proposed, which uses the state changes of the vulnerability life cycle to model the attack and defense behavior, calculates the benefits of both attack and defense through the evaluation of the exploitability of the vulnerability, and then quantifies the security situation value. We carried out the experiments using the vulnerability dataset, which was obtained by scanning the IP addresses of several enterprises in Hebei Province, China. The experimental results show that the approach of using network security vulnerabilities to assess network security status is feasible. © 2023, ICST Institute for Computer sciences, Social Informatics and Telecommunications engineering.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Fed-AugMix: Balancing Privacy and Utility via data Augmentation

arXiv

引用

arXiv 2024年

作者： Li, Haoyang Chen, Wei Zhang, Xiaojin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Laboratory Cluster and Grid Computing Laboratory School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China School of Software Engineering Huazhong University of Science and Technology Wuhan430074 China

Gradient leakage attacks pose a significant threat to the privacy guarantees of federated learning. While distortion-based protection mechanisms are commonly employed to mitigate this issue, they often lead to notable performance degradation. Existing methods struggle to preserve model performance while ensuring privacy. To address this challenge, we propose a novel data augmentation-based framework designed to achieve a favorable privacy-utility trade-off, with the potential to enhance model performance in certain cases. Our framework incorporates the AugMix algorithm at the client level, enabling data augmentation with controllable severity. By integrating the Jensen-Shannon divergence into the loss function, we embed the distortion introduced by AugMix into the model gradients, effectively safeguarding privacy against deep leakage attacks. Moreover, the JS divergence promotes model consistency across different augmentations of the same image, enhancing both robustness and performance. Extensive experiments on benchmark datasets demonstrate the effectiveness and stability of our method in protecting privacy. Furthermore, our approach maintains, and in some cases improves, model performance, showcasing its ability to achieve a robust privacy-utility trade-off. Copyright © 2024, The Authors. All rights reserved.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Working Smarter Not Harder: Hybrid Cooling for Deep Learning in Edge datacenters

IEEE Transactions on Sustainable Computing

引用

IEEE Transactions on Sustainable Computing 2025年

作者： Pei, Qiangyu Yuan, Yongjie Hu, Haichuan Wang, Lin Zhang, Dong Yan, Bingheng Yu, Chen Liu, Fangming Huazhong University of Science and Technology 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 1037 Luoyu Road Wuhan430074 China Paderborn University TU Darmstadt Germany Jinan Inspur Data Co. Ltd. China Huazhong University of Science and Technology Peng Cheng Laboratory China

The proliferation of deep-learning-based mobile and IoT applications has driven the increasing deployment of edge datacenters equipped with domain-specific accelerators. The unprecedented computing power offered by these accelerators puts a heavy burden on the cooling system, motivating more potent cooling techniques like cold water cooling. However, we observe that cold water cooling results in significant energy waste in edge datacenters due to the fluctuating resource utilization both spatially and temporally. To tackle this issue, we propose the concept of "working smarter"by slowing down accelerators deliberately whenever possible and enabling warm water cooling during these times to achieve cooling efficiency. Based on this concept, we develop Hyco - a hybrid water cooling system tailored for edge datacenters running deep learning workloads. First, Hyco features a zone-based cooling architecture enabling dynamic switching between cold water and warm water cooling. Then, based on a lightweight latency estimation method, Hyco incorporates a learning-based scheduling scheme to determine "which"accelerator workers and "when"to slow down through an adaptive and intelligent power-latency trade-off for deep learning models. The simulation with real-world traces shows that Hyco reduces the cooling energy consumption by up to 34.74× while satisfying latency constraints more than 99% of the time for deep-learning-based applications. © 2016 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Hybrid Cat-Artificial Fish Swarm Based Node Deployment Optimization in Intelligent Transportation IoT 19

Hybrid Cat-Artificial Fish Swarm Based Node Deployment Optim...

引用

2022 IEEE SmartWorld, 19th IEEE International Conference on Ubiquitous Intelligence and Computing, 2022 IEEE International Conference on Autonomous and Trusted Vehicles Conference, 22nd IEEE International Conference on Scalable Computing and Communications, 2022 IEEE International Conference on Digital Twin, 8th IEEE International Conference on Privacy Computing and 2022 IEEE International Conference on Metaverse, SmartWorld/UIC/ATC/ScalCom/DigitalTwin/PriComp/Metaverse 2022

作者： Yi, Lingzhi Luo, Bin Zhu, Chenlu Deng, Xianjun Xia, Yunzhi Wu, Hengshan Zhongnan University of Economics and Law School of Information and Safety Engineering Wuhan430073 China University of South China School of Civil Engineering Hengyang421001 China Huazhong University of Science and Technology Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Wuhan430074 China Hubei Chutian Expressway Digital Technology Co. Ltd Wuhan430074 China

ISBN: (纸本)9798350346558

The integration of Internet of Things (IoT)-based highway bridge structural health monitoring (HBSHM) and intelligent transportation systems (ITS) plays an essential role in detecting damage for large and complex bridge structures. The HBSHM provides ITS with bridge health condition information for real-time traffic management. The ITS provides HBSHM with the required traffic data to improve the HBSHM system's accuracy and reliability. Node deployment optimization (NDO) is critical in HBSHM as sensor node deployment directly affects the quality of collected data. To better solve the NDO problem in HBSHM, a novel hybrid cat-artificial fish swarm algorithm (CAT-AFSA) based on the Artificial Fish Swarm Algorithm (AFSA) and Cat Swarm optimization (CSO) is proposed in this paper. The algorithm introduces seeking and tracing behaviors of CSO into AFSA, which effectively expands the search space of artificial fish and reduces the blind search of it. The performance of the CAT-AFSA is first tested using four benchmark functions, and then its validity and feasibility for the NDO are verified using an engineering example. The simulations demonstrate that the CAT-AFSA has better search performance and computational efficiency compared with the AFSA and CSO. The CAT-AFSA has a broad application prospect in the field of NDO in civil engineering. © 2022 IEEE.

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Social Internet of Tings Trust Management Based on Implicit Social Relationship 5th

Social Internet of Tings Trust Management Based on Implicit ...

引用

5th International Conference on security and Privacy in New Computing Environments, SPNCE 2022

作者： Zhang, Hongbin Fan, Fan Zhao, Dongmei Liu, Bin Wang, Yanxia Liu, Jian School of Information Science and Engineering Hebei University of Science and Technology Shijiazhuang050000 China Hebei Key Laboratory of Network and Information Security Hebei Normal University Hebei Shijiazhuang050024 China School of Economics and Management Hebei University of Science and Technology Shijiazhuang050000 China Research Center of Big Data and Social Computing Hebei University of Science Shijiazhuang China Hebei Geological Workers’ University Shijiazhuang050081 China

ISBN: (纸本)9783031306228

The "Social Internet of Things (SIoT)" is a combination of the Internet of Things (IoT) and social networks to form a new paradigm. The SIoT promotes the development of smart cities, smart transportation, and many other fields. In SIoT, the openness and mobility of objects are enhanced. However, this tends to lead to network data sparsity problems. By distinguishing explicit and implicit social relationships, we introduce an implicit social relationship-based trust management model (IRTM) for reliable service delivery in SIoT. IRTM establishes implicit social relationships among nodes by mining their latent characteristics and trust transitivity. It models SIoT by creating sub-networks for each social relationship as a way to fuse the impact of different types of social relationships on trust management. To address the problem of malicious attacks by malicious nodes in the network to protect their interests, it considers two metrics, node relationship strength, and recommendation reliability, to filter malicious recommendations. Experiments conducted in the presence of data sparsity and malicious objects show that IRTM can improve the accuracy and convergence of trust evaluation compared to other methods that ignore implicit social relationships when computing trust. In addition, our scheme can improve resistance to trust-related attacks. © 2023, ICST Institute for Computer sciences, Social Informatics and Telecommunications engineering.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Efficient Hardware Redo Logging for Secure Persistent Memory 23

Efficient Hardware Redo Logging for Secure Persistent Memory

引用

23rd IEEE International Conference on High Performance Computing and Communications, 7th IEEE International Conference on data science and Systems, 19th IEEE International Conference on Smart City and 7th IEEE International Conference on Dependability in Sensor, Cloud and big data Systems and Applications, HPCC-DSS-SmartCity-DependSys 2021

作者： Zhang, Zhan Yue, Jianhui Liao, Xiaofei Jin, Hai School of Computer Science and Technology Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab Wuhan China Michigan Technological University Computer Science Department HoughtonMI United States

ISBN: (纸本)9781665494571

Write-ahead log and data encryption technologies are employed to ensure both crash consistency and data security for persistent memory (PM). The encryption/decryption of both data and log requests increase the memory request latency, degrading the system performance. To tackle this issue, this paper proposes a novel log-aware memory encryption scheme to reduce encryption/decryption operations, without compromising data security. Specifically, redo log blocks are stored as ciphertext for their corresponding data blocks to avoid encryption/decryption of log data blocks when in-place update operations are applied to them. We further design a compact log record layout with fewer encryption metadata in log records to reduce logging traffic. Our simulation results show that the transaction throughput of the proposed design outperforms the baseline design and the state-of-the-art design by 87.3% and 55.3% on average, respectively. © 2021 IEEE.

关键词： Smart cities System performance Simulation Memory management Layout Memory architecture Metadata

来源：评论

学校读者我要写书评

暂无评论

X-Stream: A Flexible, Adaptive Video Transformer for Privacy-Preserving Video Stream Analytics

X-Stream: A Flexible, Adaptive Video Transformer for Privacy...

引用

IEEE Annual Joint Conference: INFOCOM, IEEE Computer and Communications Societies

作者： Dou Feng Lin Wang Shutong Chen Lingching Tung Fangming Liu 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 China 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 Paderborn University Germany 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 Guangxi University China 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 Peng Cheng Laboratory China

ISBN: (数字)9798350383508

ISBN: (纸本)9798350383515

Video stream analytics (VSA) systems fuel many exciting applications that facilitate people’s lives, but also raise critical concerns about exposing too much individuals’ privacy. To alleviate these concerns, various frameworks have been presented to enhance the privacy of VSA systems. Yet, existing solutions suffer two limitations: (1) being scenario-customized, thus limiting the generality of adapting to multifarious scenarios, (2) requiring complex, imperative programming, and tedious process, thus largely reducing the usability of such systems. In this paper, we present X-Stream, a privacy-preserving video transformer that achieves flexibility and efficiency for a large variety of VSA tasks. X-Stream features three major novel designs: (1) a declarative query interface that provides a simple yet expressive interface for users to describe both their privacy protection and content exposure requirements, (2) an adaptation mechanism that dynamically selects the most suitable privacy-preserving techniques and their parameters based on the current video context, and (3) an efficient execution engine that incorporates optimizations for multi-task deduplication and inter-frame inference. We implement X-Stream and evaluate it with representative VSA tasks and public video datasets. The results show that X-Stream achieves significantly improved privacy protection quality and performance over the state-of-the-art, while being simple to use.

关键词： Privacy Transforms Streaming media Transformers Multitasking Real-time systems Task analysis

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：