检索结果-内蒙古大学图书馆

Dual defense:Combining preemptive exclusion of members and knowledge distillation to mitigate membership inference attacks

引用

Journal of Information and Intelligence 2025年第1期3卷 68-90页

作者： Jun Niu Peng Liu Chunhui Huang Yangming Zhang Moxuan Zeng Kuo Shen Yangzhong Wang Suyu An Yulong Shen Xiaohong Jiang Jianfeng Ma He Wang Gaofei Wu Anmin Fu Chunjie Cao Xiaoyan Zhu Yuqing Zhang School of Computer Science and Technology Xidian UniversityXi'an 710071China Information Sciences and Technology Pennsylvania State UniversityPA 16802USA School of Cyberspace Security Hainan UniversityHaikou 570228China School of Hangzhou Institute of Technology Xidian UniversityHangzhou 311231China School of Systems Information Science Future University of HakodateHakodate 041-8655Japan School of Cyber Engineering Xidian UniversityXi'an 710071China School of Computer Science and Engineering Nanjing University of Science and TechnologyNanjing 210094China School of Telecommunications Engineering Xidian UniversityXi'an 710071China School of Computer&Control Engineering University of Chinese Academy of SciencesBeijing 101408China

Membership inference(MI)attacks threaten user privacy through determining if a given data example has been used to train a target *** MI defenses protect the membership privacy through preemptive exclusion of members techniques and knowledge ***,using either of these two defenses alone,the defense effect can still offers an unsatisfactory trade-off between membership privacy and *** that the defense method that directly combines these two defenses is still very limited(e.g.,the test accuracy of the target model is decreased by about 40%(in our experiments)),in this work,we propose a dual defense(DD)method that includes the preemptive exclusion of high-risk member samples module and the knowledge distillation module,which thwarts the access of the resulting models to the private training data twice to mitigate MI *** defense method can be divided into two steps:the preemptive exclusion of high-risk member samples(Step 1)and the knowledge distillation to obtain the protected student model(Step 2).We propose three types of exclusions:existing MI attacks-based exclusions,sample distances of members and nonmembers-based exclusions,and mutual information value-based exclusions,to preemptively exclude the high-risk member *** the knowledge distillation phase,we add ground-truth labeled data to the reference dataset to decrease the protected student model's dependency on soft labels,aiming to maintain or improve its test *** evaluation shows that DD significantly outperforms state-of-the-art defenses and offers a better privacy-utility *** example,DD achieves∼100%test accuracy improvement over the distillation for membership privacy(DMP)defense for ResNet50 trained on *** simultaneously achieves the reductions in the attack effectiveness(e.g.,the TPR@0.01%FPR of enhanced MI attacks decreased by 2.10%on the ImageNet dataset,the membership advantage(MA)of risk score-based attacks d

关键词： Machine learning Membership inference defenses Preemptive exclusion Knowledge distillation

来源：评论

学校读者我要写书评

暂无评论

Cluster-Refined Optimal Transport for Unsupervised Action Segmentation

Cluster-Refined Optimal Transport for Unsupervised Action Se...

引用

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

作者： Shijie Wang Jinrong Zhang Yule Liu Shiyao Li Lin Feng School of Computer Science and Technology Dalian University of Technology Dalian China School of Control Science and Engineering Dalian University of Technology Dalian China School of Innovation and Entrepreneurship Dalian University of Technology Dalian China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Action segmentation in untrimmed videos is essential for comprehensive video understanding. Despite significant progress in unsupervised methods, capturing both long-range dependencies and short-duration actions simultaneously remains a challenging task. To address this challenge, this paper introduces the Cluster-Refined Optimal Transport (CROT) method, combining hierarchical clustering and optimal transport for unsupervised action segmentation. We first hierarchically cluster video frame representations to capture long-range dependencies and generate pseudo-boundaries. Initial pseudo-labels are then obtained via optimal transport, ensuring short-duration actions are recognized. Finally, these pseudo-labels are refined using the pseudo-boundaries, resulting in the final segmentation output. Extensive experiments on three public datasets, i.e., YouTube Instructions, Breakfast, and 50Salads, demonstrate that our method performs on par with or better than previous approaches.

关键词： Video on demand Signal processing Acoustics Web sites Speech processing Videos

来源：评论

学校读者我要写书评

暂无评论

Image Inversion: A Survey from GANs to Diffusion and Beyond

arXiv

引用

arXiv 2025年

作者： Chen, Yinan Zhang, Jiangning Bi, Yali Hu, Xiaobin Hu, Teng Xue, Zhucun Yi, Ran Liu, Yong Tai, Ying College of Control Science and Engineering Zhejiang University China YouTu Lab Tencent China College of Computer and Information Science Southwest University China Department of Computer Science & Engineering Shanghai Jiao Tong University China School of Intelligence Science and Technology Nanjing University China

Image inversion is a fundamental task in generative models, aiming to map images back to their latent representations to enable downstream applications such as editing, restoration, and style transfer. This paper provides a comprehensive review of the latest advancements in image inversion techniques, focusing on two main paradigms: Generative Adversarial Network (GAN) inversion and diffusion model inversion. We categorize these techniques based on their optimization methods. For GAN inversion, we systematically classify existing methods into encoder-based approaches, latent optimization approaches, and hybrid approaches, analyzing their theoretical foundations, technical innovations, and practical trade-offs. For diffusion model inversion, we explore training-free strategies, fine-tuning methods, and the design of additional trainable modules, highlighting their unique advantages and limitations. Additionally, we discuss several popular downstream applications and emerging applications beyond image tasks, identifying current challenges and future research directions. By synthesizing the latest developments, this paper aims to provide researchers and practitioners with a valuable reference resource, promoting further advancements in the field of image inversion. We keep track of the latest works at https://***/RyanChenYN/ImageInversion. Copyright © 2025, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Climate Downscaling Using Neural Operator: Spatiotemporal Multimodal Fusion Operator with State-Query Coupled Kernel

Climate Downscaling Using Neural Operator: Spatiotemporal Mu...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Zhang, Haodi Wang, Yichi Jian, Yifan Jiang, Jiahui Bai, Zhaohai Ma, Lin College of Computer Science and Software Engineering Shenzhen University China Center for Agricultural Resources Research Institute of Genetic and Developmental Biology Chinese Academy of Sciences China State Key Laboratory of Pollution Control and Resource Reuse School of the Environment Nanjing University China

ISBN: (纸本)9798350368741

Climate downscaling is crucial for detailed small-scale analysis and for acquiring climate data in regions without weather stations. Operator learning has proven potential for this task. However, several challenges remain in operator learning, such as multimodal fusion, spatiotemporal fusion and input state and query adaptation. To address these challenges, we propose a Spatiotemporal Multimodal Fusion Operator with a State-Query Coupled Kernel (SMCK). This framework includes a latent space fusion encoder that encodes climate variables using position-wise multihead attention for multimodal fusion and integrates historical information to generate robust and precise representation. Additionally, we introduce a state-query coupled kernel that combines radial basis functions and discrete fourier encoding to enhance query location representation, while also adapting to the state to obtain the coupled kernel. Extensive experiments demonstrate that our method achieves state-ofthe-art performance and provides strong support for climate downscaling and the planning of climate-related strategies. © 2025 IEEE.

关键词： Climate downscaling Deep Learning Multimodal fusion Operator learning Time series forecasting

来源：评论

学校读者我要写书评

暂无评论

Multiagent Confrontation Method Based on Three-Party Dynamic Multistrategy Evolutionary Game

引用

IEEE Transactions on Computational Social Systems 2025年

作者： Jin, Shilong Wang, Yingjie Duan, Peiyong Zhang, Haijing Li, Gang Cai, Zhipeng Yantai University School of Computer and Control Engineering Yantai264005 China Qilu University of Technology Shandong Academy of Sciences Faculty of Electronics Electrical and Control Jinan250353 China Georgia State University Department of Computer Science AtlantaGA30303 United States

Unmanned agents represent a significant advancement in unmanned control and constitute an important element in the future agent warfare. Their autonomous decision-making capabilities are integral to accomplishing tasks independently. To address challenges inherent in multiparty game scenarios that traditional method struggle with and enhance the applicability and accuracy of game decision-making, this article proposes a novel multiagent confrontation method for unmanned vessels, tailored to a three-party dynamic multistrategy evolutionary game in incomplete information scenarios. The approach introduces a new incentive mechanism designed to enhance both individual and collective profits of agents. Using evolutionary game theory, a three-party model is developed, incorporating interactions among player, enemy, and neutral agents. The model tracks the evolution of strategies to identify stable equilibria across various perceptual conditions. Simulations validate the effectiveness of the proposed method in selecting optimal strategies for unmanned vessels in complex battlefield scenarios, demonstrating its potential for improving autonomous decision-making in multiparty confrontations. © 2014 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

HaloFL: Efficient Heterogeneity-Aware Federated Learning Through Optimal Submodel Extraction and Dynamic Sparse Adjustment

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and Systems 2025年

作者： Lian, Zirui Cao, Qianyue Liang, Chao Cao, Jing Zhu, Zongwei Yang, Zhi Ji, Cheng Li, Changlong Zhou, Xuehai School of Computer Science and Technology University of Science and Technology of China Hefei230026 China Suzhou Institute for Advanced Research University of Science and Technology of China Suzhou215123 China School of Software Engineering University of Science and Technology of China Hefei230026 China Xi'an Modern Control Technology Research Institute China Dfh satellite co. Ltd Cast China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China School of Computer Science and Technology East China Normal University Shanghai200063 China

Federated Learning (FL) is an advanced framework that enables collaborative training of machine learning models across edge devices. An effective strategy to enhance training efficiency is to allocate the optimal submodel based on each device's resource capabilities. However, system heterogeneity significantly increases the difficulty of allocating submodel parameter budgets appropriately for each device, leading to the straggler problem. Meanwhile, data heterogeneity complicates the selection of the optimal submodel structure for specific devices, thereby impacting training performance. Furthermore, the dynamic nature of edge environments, such as fluctuations in network communication and computational resources, exacerbates these challenges, making it even more difficult to precisely extract appropriately sized and structured submodels from the global model. To address the challenges in heterogeneous training environments, we propose an efficient FL framework, namely HaloFL. The framework dynamically adjusts the structure and parameter budget of submodels during training by evaluating three dimensions: model-wise performance, layer-wise performance, and unit-wise performance. First, we design a data-aware model unit importance evaluation method to determine the optimal submodel structure for different data distributions. Next, using this evaluation method, we analyze the importance of model layers and reallocate parameters from non-critical layers to critical layers within a fixed parameter budget, further optimizing the submodel structure. Finally, we introduce a resource-aware dual-UCB multi-armed bandit agent, which dynamically adjusts the total parameter budget of submodels according to changes in the training environment, allowing the framework to better adapt to the performance differences of heterogeneous devices. Experimental results demonstrate that HaloFL exhibits outstanding efficiency in various dynamic and heterogeneous scenarios, achieving up to a 14

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A survey of distributed algorithms for aggregative games

引用

IEEE/CAA Journal of Automatica Sinica 2025年第5期12卷 859-871页

作者： Li, Huaqing Li, Jun Ran, Liang Zheng, Lifeng Huang, Tingwen Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing The College of Electronic and Information Engineering Southwest University Chongqing400715 China College of Computer Science and Engineering Chongqing University of Technology Chongqing400054 China School of Computer Science and Control Engineering Shenzhen University of Advanced Technology Shenzhen518107 China

Game theory-based models and design tools have gained substantial prominence for controlling and optimizing behavior within distributed engineering systems due to the inherent distribution of decisions among individuals. In non-cooperative settings, aggregative games serve as a mathematical framework model for the interdependent optimal decision-making problem among a group of non-cooperative players. In such scenarios, each player's decision is influenced by an aggregation of all players' decisions. Nash equilibrium (NE) seeking in aggregative games has emerged as a vibrant topic driven by applications that harness the aggregation property. This paper presents a comprehensive overview of the current research on aggregative games with a focus on communication topology. A systematic classification is conducted on distributed algorithm research based on communication topologies such as undirected networks, directed networks, and time-varying networks. Furthermore, it sorts out the challenges and compares the algorithms' convergence performance. It also delves into real-world applications of distributed optimization techniques grounded in aggregative games. Finally, it proposes several challenges that can guide future research directions. © 2025 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.

关键词： Nash equilibrium

来源：评论

学校读者我要写书评

暂无评论

Resilient Cooperative control of Multiple DC Microgrids With Interconnection Networks Against Cyber Attacks

IEEE Transactions on Industrial Cyber-Physical Systems

引用

IEEE Transactions on Industrial Cyber-Physical Systems 2025年 3卷 116-126页

作者： Xiao, Feng Liu, Shiyu Wei, Bo Fang, Fang Qin, Jiahu North China Electric Power University State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources Beijing102206 China North China Electric Power University School of Control and Computer Engineering Beijing102206 China North China Electric Power University New Energy Generation National Engineering Research Center Beijing102206 China University of Science and Technology of China Department of Automation Hefei230027 China

The two control objectives of voltage regulation and precise current sharing are conflicting in multi-bus DC microgrids. In this paper, a distributed control strategy is proposed, and it can achieve accurate current sharing and regulate the voltage of a critical node to the rated value. However, such a distributed control system is susceptible to potential cyber attacks that could deteriorate microgrids performances by corrupting communication links or actuators. To overcome these difficulties, we design the interconnected communication networks to establish a resilient cooperative system of multiple microgrids against unknown bounded injection attacks. The proposed resilient control strategy can achieve the control objectives of maintaining voltage regulation and current sharing within each microgrids under different operating conditions, and the interconnected system consisting of multiple microgrids cooperates to mitigate the adverse effect of cyber attacks. The dynamics and stability of the overall close-loop system of the DC microgrids are analyzed, in the present or absent of cyber attacks. Simulation results validate the effectiveness of the proposed approach in two 4-bus DC microgrids. © 2023 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Intelligent Construction and Analysis of a Complex Network for Determining Risk-Influencing Factors in Ship Self-Sinking Accidents

引用

ASCE-ASME Journal of Risk and Uncertainty in engineering Systems, Part A: Civil engineering 2025年第3期11卷

作者： Ma, Jun Wang, Liguang Xu, Luhui Zhao, Jiong Lin, Rui School of Computer Science Xijing Univ. Xi'An Key Laboratory of Human-Machine Integration and Control Technology for Intelligence Xi'an710123 China School of Computer Science Xijing Univ. Xi'an710123 China Xi'An Senke Construction Engineering Co. Xi'an710043 China

One of the most effective methods for analyzing risk-influencing factors (RIFs) in maritime accidents is the complex network approach. However, there is limited research specifically focused on RIFs in ship self-sinking accidents. Moreover, challenges remain in the accurate ontology construction of RIFs based on the data set, intelligent extraction of RIF propagation paths, RIF importance ranking, and robustness analysis of complex networks. To address these issues, an intelligent method is proposed to construct a ship self-sinking accident RIF complex network (SSARIFCN) based on 204 accident reports, yielding 247 nodes and 1,872 edges derived from 488 RIF propagation paths. This approach significantly improves the objectivity and accuracy of RIF identification while enhancing the intelligence level of the information extraction process. The three-weight LeaderRank algorithm is applied for node importance ranking and network robustness analysis, outperforming eight traditional ranking models and five attack algorithms, enhancing the accuracy of key RIF identification. Based on this algorithm, the top five RIFs for ship self-sinking accidents were identified, concluding that "unfit for maritime navigation"is a frequently overlooked key RIF. The experiment validates the method's effectiveness in identifying key RIFs, controlling RIF propagation, and enhancing accident prevention and navigational safety. © 2025 American Society of Civil Engineers.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Causal Discovery from Shifted Multiple Environments 25

Causal Discovery from Shifted Multiple Environments

引用

Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1

作者： Dezhi Yang Guoxian Yu Jun Wang Jinglin Zhang Carlotta Domeniconi School of Software Shandong University Jinan Shandong China School of Control Science and Engineering Shandong University Jinan Shandong China Department of Computer Science George Mason University Fairfax VA USA

ISBN: (纸本)9798400712456

A fundamental problem in many science domains is learning the causal structure of a system from observed data. The observed data canonically come from multiple environments (i.e. different times, locations, and measurements), and causal models may have unobserved shifts. Although the causal graphs can be identified by modeling the distribution changes among different environments, existing solutions can only learn causal structures when given environmental information. In contrast, we propose a causal discovery approach (CausalSME) which automatically identifies pseudo environments and unobserved distribution shifts. Specifically, CausalSME learns a causal model containing unobserved variables, which can correct the distribution shifts with mixed environments. The heart of CausalSME is a variational autoencoder that infers shifted causal effects of unobserved variables and guides the identification of environment information. It further divides the shifted samples by the identified environments to jointly learn an invariant causal model. We prove the structure identifiability of CausalSME with the causal additive model. In our extensive experiments we show that CausalSME achieves state-of-the-art performance.

关键词： adversarial learning

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：