检索结果-内蒙古大学图书馆

VFLMonitor: Defending One-Party Hijacking Attacks in Vertical Federated Learning

IEEE Transactions on Information Forensics and security 2025年 20卷 4828-4843页

作者： Xu, Xiangrui Zhao, Yiwen Han, Yufei Zhu, Yongsheng Han, Zhen Xu, Guangquan Wang, Bin Ji, Shouling Wang, Wei Qingdao University of Science and Technology School of Information Science and Technology Qingdao266061 China University of Southern California Thomas Lord Department of Computer Science Los AngelesCA90007 United States INRIA Brittany Rennes35042 France Institute of Computing Technologies China Academy of Railway Sciences Corporation Ltd. Beijing100081 China Beijing Jiaotong University Beijing Key Laboratory of Security and Privacy in Intelligent Transportation Beijing100044 China College of Intelligence and Computing Tianjin300072 China Network and Data Security Hangzhou310053 China Zhejiang University College of Computer Science and Technology Zhejiang 310058 China Xi’an Jiaotong University Ministry of Education Key Laboratory for Intelligent Networks and Network Security Xi’an710049 China

Vertical Federated Learning (VFL) is susceptible to various one-party hijacking attacks, such as Replay and Generation attacks, where a single malicious client can manipulate the model to produce attacker-specified results, thereby compromising its reliability in real-world deployments. In this paper, we first uncover the underlying mechanisms of these attacks and observe that successful attacks induce significant discrepancies in the embedding-label associations across different clients. We establish a theoretical framework demonstrating how these discrepancies can serve as reliable indicators for detecting hijacking attempts. Building upon this insight, we propose VFLMonitor, a robust defense mechanism that leverages these embedding-label discrepancies to detect and mitigate hijacking attacks. Specifically, VFLMonitor identifies suspicious queries by analyzing differences in label estimations from multiple clients and applies a majority voting rule to correct or filter out these malicious queries. Moreover, VFLMonitor introduces a novel regularization strategy during training to reduce intra-class variance in embeddings, thereby enhancing their discriminative power and improving defense effectiveness. Extensive experiments were conducted on 5 real-world datasets against 2 different attack types under 3 attack scenarios. The results demonstrate that VFLMonitor can effectively identify and exclude potential hijacked requests in all types of one-party hijacking attacks, while maintaining a meager false positive rate for legitimate queries. © 2005-2012 IEEE.

关键词： Training Servers Electronic mail Artificial intelligence Reliability theory Predictive models Federated learning Data models Computational modeling Collaboration

来源：评论

学校读者我要写书评

暂无评论

Leveraging semantic relations in code and data to enhance taint analysis of embedded systems 24

Leveraging semantic relations in code and data to enhance ta...

引用

Proceedings of the 33rd USENIX Conference on security Symposium

作者： Jiaxu Zhao Yuekang Li Yanyan Zou Zhaohui Liang Yang Xiao Yeting Li Bingwei Peng Nanyu Zhong Xinyi Wang Wei Wang Wei Huo Institute of Information Engineering Chinese Academy of Sciences China and School of Cyber Security University of Chinese Academy of Sciences China and Key Laboratory of Network Assessment Technology Chinese Academy of Sciences China and Beijing Key Laboratory of Network Security and Protection Technology China University of New South Wales Australia Institute of Information Engineering Chinese Academy of Sciences China and Key Laboratory of Network Assessment Technology Chinese Academy of Sciences China and Beijing Key Laboratory of Network Security and Protection Technology China

ISBN: (纸本)9781939133441

IoT devices have significantly impacted our daily lives, and detecting vulnerabilities in embedded systems early on is critical for ensuring their security. Among the existing vulnerability detection techniques for embedded systems, static taint analysis has been proven effective in detecting severe vulnerabilities, such as command injection vulnerabilities, which can cause remote code execution. Nevertheless, static taint analysis is faced with the problem of identifying sources comprehensively and *** paper presents LARA, a novel static taint analysis technique to detect vulnerabilities in embedded systems. The design of LARA is inspired by an observation that pertains to semantic relations within and between the code and data of embedded software: user input entries can be categorized as URIs or keys (data), and identifying their handling code (code) and relations can help systematically and comprehensively identify the sources for taint analysis. Transforming the observation into a practical methodology poses challenges. To address these challenges, LARA employs a combination of pattern-based static analysis and large language model(LLM)-aided analysis, aiming to replicate how human experts would utilize the findings during analysis and enhance it. The pattern-based static analysis simulates human experience, while the LLM-aided analysis captures the way human experts perceive code semantics. We implemented LARA and evaluated it on 203 IoT devices from 21 vendors. In general, LARA detects 556 and 602 more known vulnerabilities than SATC and KARONTE while reducing false positives by 57.0% and 54.3%. Meanwhile, with more sources and sinks from LARA, EMTAINT can detect 245 more vulnerabilities. To date, LARA has found 245 0-day vulnerabilities in 57 devices, all of which were confirmed or fixed with 162 CVE IDs assigned.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fine-grained Personalized Hierarchical Federated Learning towards Heterogeneous Internet of Vehicles

引用

IEEE Internet of Things Journal 2025年第11期12卷 16349-16362页

作者： Zhang, Puning Shao, Shuman Wu, Chao Yang, Zhigang Zhang, Ruoying Chongqing University of Posts and Telecommunications School of Communications and Information Engineering Chongqing400065 China Chongqing Key Laboratory of Ubiquitous Sensing and Networking Advanced Network and Intelligent Connection Technology Key Laboratory of Chongqing Education Commission of China Chongqing400065 China Chongqing Innovation Center of Industrial Big-Data Co. Ltd National Engineering Laboratory for Industrial Big-data Application Technology Chongqing400707 China China Merchants Testing Vehicle Technology Research Institute Co. Ltd Chongqing404100 China Chongqing University of Posts and Telecommunications School of Cyber Security and Information Law Chongqing400065 China Chongqing Key Laboratory of Ubiquitous Sensing and Networking Advanced Network and Intelligent Connection Technology Key Laboratory of Chongqing Education Commission of China China China Academy of Information and Communications Beijing100083 China

High mobility and non-independent and identically distributed (non-iid) data in the Internet of Vehicles (IoV) pose challenges for the convergence speed and accuracy of federated learning model training. Traditional federated learning approaches fail to account for the unique characteristics of local vehicle data, limiting the model performances. To address this, we propose a personalized hierarchical federated learning method tailored for heterogeneous IoV. Our approach customizes models for each vehicle, enhancing their performance on local data. We introduce a network-aware client selection method that dynamically chooses vehicle clients based on their spatiotemporal distribution and changing channel conditions. Additionally, our fine-grained personalized learning method leverages frequency domain analysis to extract and retain both fundamental and personalized knowledge from local model parameters. This allows us to build highly accurate personalized models suited to each vehicle's data characteristics. Experimental results show that our method improves model accuracy by up to 10.31% and reduces training time by up to 24.93% compared to the latest personalized federated learning algorithms. © 2025 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Disentangled Noisy Correspondence Learning

引用

IEEE Transactions on Image Processing 2025年 34卷 2602-2615页

作者： Dang, Zhuohang Luo, Minnan Wang, Jihong Jia, Chengyou Han, Haochen Wan, Herun Dai, Guang Chang, Xiaojun Wang, Jingdong Xi’an Jiaotong University School of Computer Science and Technology Ministry of Education Key Laboratory of Intelligent Networks and Network Security Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Shaanxi Xi’an710049 China SGIT AI Laboratory Xi’an710048 China State Grid Corporation of China State Grid Shaanxi Electric Power Company Ltd. Xi’an710048 China University of Science and Technology of China School of Information Science and Technology Hefei230026 China Abu Dhabi United Arab Emirates Baidu Inc. Beijing100085 China

Cross-modal retrieval is crucial in understanding latent correspondences across modalities. However, existing methods implicitly assume well-matched training data, which is impractical as real-world data inevitably involves imperfect alignments, i.e., noisy correspondences. Although some works explore similarity-based strategies to address such noise, they suffer from sub-optimal similarity predictions influenced by modality-exclusive information (MEI), e.g., background noise in images and abstract definitions in texts. This issue arises as MEI is not shared across modalities, thus aligning it in training can markedly mislead similarity predictions. Moreover, although intuitive, directly applying previous cross-modal disentanglement methods suffers from limited noise tolerance and disentanglement efficacy. Inspired by the robustness of information bottlenecks against noise, we introduce DisNCL, a novel information-theoretic framework for feature Disentanglement in Noisy Correspondence Learning, to adaptively balance the extraction of modality-invariant information (MII) and MEI with certifiable optimal cross-modal disentanglement efficacy. DisNCL then enhances similarity predictions in modality-invariant subspace, thereby greatly boosting similarity-based alleviation strategy for noisy correspondences. Furthermore, DisNCL introduces soft matching targets to model noisy many-to-many relationships inherent in multi-modal inputs for noise-robust and accurate cross-modal alignment. Extensive experiments confirm DisNCL’s efficacy by 2% average recall improvement. Mutual information estimation and visualization results show that DisNCL learns meaningful MII/MEI subspaces, validating our theoretical analyses. © 1992-2012 IEEE.

关键词： Information theory

来源：评论

学校读者我要写书评

暂无评论

Variability of mechanical properties of geopolymer recycled aggregate concrete: Experimental and numerical study

引用

Construction and Building Materials 2025年 477卷

作者： Zhou, Hongyuan Mu, Chongyuan Wang, Xiaojuan Song, Tianyi Zhang, Hong Wang, Yonghui Key Laboratory of Urban Security and Disaster Engineering of Ministry of Education Beijing University of Technology Beijing100124 China State Key Laboratory of Explosion Science and Safety Protection Beijing Institute of Technology Beijing100081 China Key Laboratory of Structures Dynamic Behaviour and Control of the Ministry of Education Harbin Institute of Technology Harbin150090 China

Despite the extensive research available on the mechanical properties of geopolymer recycled aggregate concrete (GRAC), its variability has received insufficient attention, potentially posing significant risks to the safety of GRAC components in practical applications. To further investigate the influence of specimen widths, height-to-width ratios, and RCA substitution rates on the mechanical performance variability of GRAC, GRAC specimens were fabricated for the quasi-static compressive test and the corresponding numerical simulations were conducted. First, the GRAC specimens with four different specimen widths (70, 100, 150, and 200 mm) and five different RCA substitution rates (0 %, 30 %, 50 %, 70 %, and 100 %) were fabricated for the quasi-static compressive test. Subsequently, a non-homogeneous meso-scale numerical model, accounting for the correlation among compressive strength, elastic modulus, and peak strain using the third-moment normal transformation (TMNT) method, was proposed and validated by the test data. The experimental and numerical results demonstrated that, compared to normal and log-normal distribution models, the Weibull distribution model could more accurately describe the compressive strength distribution of GRAC with a smaller prediction error. Furthermore, it was observed that compressive strength variability of GRAC decreased with an increase in specimen width and height-to-width ratio, while initially increasing and then decreasing with an increase in RCA substitution rate. In addition, based on the experimental and numerical results, the compressive strength prediction formula for GRAC at any specified reliability was proposed, accounting for specimen width, height-to-width ratio, and RCA substitution rate. It offered a more accurate prediction of the compressive strength of GRAC with different specimen widths, height-to-width ratios, and RCA substitution rates at any given reliability, thereby facilitating a more rational design of GRAC

关键词： Geopolymer concrete

来源：评论

学校读者我要写书评

暂无评论

Cu single sites on BO2 as thyroid peroxidase mimicking for iodotyrosine coupling and pharmaceutical assess

引用

Science Bulletin 2025年第10期70卷 1611-1618页

作者： Hu, Lijun Li, Ruimin Chen, Chengjie Jia, Xiangkun Li, Xiaotong Jiao, Lei Zhu, Chengzhou Lu, Xiaoquan Zhai, Yanling Guo, Shaojun Institute of Molecular Metrology College of Chemistry and Chemical Engineering Qingdao University Qingdao266071 China School of Materials Science and Engineering Peking University Beijing100871 China Key Laboratory of Water Security and Water Environment Protection in Plateau Intersection Ministry of Education Key Laboratory of Bioelectrochemistry and Environmental Analysis of Gansu Province College of Chemistry and Chemical Engineering Northwest Normal University Lanzhou730070 China National Key Laboratory of Green Pesticide International Joint Research Center for Intelligent Biosensing Technology and Health College of Chemistry Central China Normal University Wuhan430079 China

Designing three-dimensional (3D) catalytic sites in single-atom catalysts (SACs) that mimic thyroid peroxidase (TPO) function for achieving iodotyrosine coupling, although highly desirable for the synthesis of thyroid hormones, poses a great challenge. Herein, we design and synthesize a class of SACs with 3D catalytic centers composed of Cu-N5 as catalytic sites and BO2 as binding sites (BO2/CuN5C) for mimicking TPO in activating H2O2 to facilitate tyrosine iodination and conjugation for producing thyroid hormones. We demonstrate that the as-prepared BO2/CuN5C not only provides binding sites for H2O2 through hydrogen bond interactions but also possesses catalytic sites to promote an alternative O–O heterolysis process. BO2/CuN5C with TPO-like catalytic centers can produce 3,3′,5-triiodothyronine and D-thyroxine with 2.4-fold and 11.1-fold improvements relative to those of CuN5C. Besides, the assessment of 2-mercapto-1-methylimidazole and 6-propyl-2-thiouracil in vitro investigations of antithyroid drugs corresponds well with the European Thyroid Association guidelines and therefore can provide clinical medication guidance to prevent toxic reactions. Overall, this work unlocks an approach to precisely simulate the natural enzyme active site for amino acid coupling and pharmaceutical assessment. © 2025 Science China Press

关键词： Hydrogen bonds

来源：评论

学校读者我要写书评

暂无评论

Across-Platform Detection of Malicious Cryptocurrency Accounts via Interaction Feature Learning

引用

IEEE Transactions on Information Forensics and security 2025年 20卷 4783-4798页

作者： Che, Zheng Shen, Meng Tan, Zhehui Du, Hanbiao Wang, Wei Chen, Ting Zhao, Qinglin Xie, Yong Zhu, Liehuang Beijing Institute of Technology School of Computer Science Beijing100081 China Beijing Institute of Technology School of Cyberspace Science and Technology Beijing100081 China Xi'an Jiaotong University Key Laboratory for Intelligent Networks and Network Security Ministry of Education Xi'an710049 China University of Electronic Science and Technology of China School of Computer Science and Engineering Chengdu611731 China Macau University of Science and Technology School of Computer Science and Engineering Taipa China Qinghai Institute of Technology School of Computer and Information Science Xining810016 China

With the rapid evolution of Web3.0, cryptocurrency has become a cornerstone of decentralized finance. While these digital assets enable efficient and borderless financial transactions, their pseudonymous nature has also attracted malicious activities such as money laundering, fraud, and other financial crimes. Effective detection of malicious accounts is crucial to maintaining the security and integrity of the Web 3.0 ecosystem. Existing malicious account detection methods rely on large amounts of labeled data and suffer from low generalization. Label-efficient and generalizable malicious account detection remains a challenging task. In this paper, we propose ShadowEyes, a framework for detecting malicious accounts by leveraging interaction feature learning with only a small labeled dataset. Specifically, We first propose a generalized account representation named TxGraph, which captures the universal interaction features of Ethereum and Bitcoin. Then we carefully design an account representation augmentation method tailored to simulate the evolution of malicious accounts to generate positive pairs. We conduct extensive experiments using public datasets to evaluate the performance of ShadowEyes. The results demonstrate that it outperforms state-of-the-art (SOTA) methods in four typical scenarios. Specifically, in the scenario of across-platform malicious account detection, ShadowEyes maintains an F1 score of around 90%, which is 10% higher than the SOTA method. In the zero-shot learning scenario, it can achieve an F1 score of 79.56% for detecting gambling accounts, surpassing the SOTA method by 10.44%. © 2005-2012 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Location Privacy Preservation Crowdsensing With Federated Reinforcement Learning

引用

IEEE Transactions on Dependable and Secure Computing 2025年第3期22卷 1877-1894页

作者： You, Zhichao Dong, Xuewen Liu, Ximeng Gao, Sheng Wang, Yongzhi Shen, Yulong Xidian University School of Computer Science and Technology The Engineering Research Center of Blockchain Technology Application and Evaluation Ministry of Education Xi'an710071 China Shaanxi Key Laboratory of Blockchain and Secure Computing Xi'an710071 China Fuzhou University College of Computer and Data Science Fuzhou350025 China Central University of Finance and Economics School of Information Beijing102206 China California State Polytechnic University Pomona Department of Computer Information Systems PomonaCA91768 United States Xidian University School of Computer Science and Technology Xi'an710071 China Shaanxi Key Laboratory of Network and System Security Xi'an710071 China

Crowdsensing has become a popular method of sensing data collection while facing the problem of protecting participants' location privacy. Existing location-privacy crowdsensing mechanisms focus on static tasks and participants without considering sensing tasks' time requirements and participants' mobility, which cannot achieve satisfactory collected data quality and task completion in crowdsensing with dynamic tasks and participants. Inspired by this, we proposed a location-preservation crowdsensing mechanism, FedSense, considering dynamic tasks and participants based on federated learning (FL) and reinforcement learning (RL). In FedSense, through RL's outstanding decision-making ability, participants select sensing tasks to perform by well-trained RL models without uploading location information to servers for task allocation. We propose an independent tasks selection environment that defines actions, states, and rewards of RL to enable FedSense to achieve satisfactory task completion and data quality while preserving location privacy. Besides, FedSense applies an asynchronous FL aggregation algorithm that reduces participants' network stabilization and device computing ability requirements. Analysis proves that participants' location information does not leave the local device during the model training and task selection process, effectively avoiding privacy leakage. Simulation shows that compared with existing location-preservation crowdsensing mechanisms, FedSense achieves the highest task completion and sensing accuracy for dynamic tasks and participants. © 2024 IEEE.

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

Research and Implementation of Trusted Blockchain Core technology Based on State Secret Algorithm

引用

China Communications 2025年第4期22卷 143-160页

作者： Zheng Qingan Meng Jialin Wu Junjie Li Jingtao Lin Haonan Computer Science and Information Security Management Department Fujian Police CollegeFuzhou 350007China Fujian Province Key Laboratory for Digital Network Crime Supervision and Prevention Fuzhou 350007China ByteDance Technology(Beijing)Co. Ltd.Haidian DistrictBeijing 100080China Dongguan Water Group Co. LtdDongguan 523000China Fuqing Municipal Public Security Bureau Fuzhou 350301China

With the rapid development of blockchain technology,the Chinese government has proposed that the commercial use of blockchain services in China should support the national encryption standard,also known as the state secret algorithm GuoMi *** original Hyperledger Fabric only supports internationally common encryption algorithms,so it is particularly necessary to enhance support for the national encryption *** identity authentication,access control,and security audit technologies have single-point failures,and data can be easily tampered with,leading to trust *** address these problems,this paper proposes an optimized and application research plan for Hyperledger *** study the optimization model of cryptographic components in Hyperledger Fabric,and based on Fabric's pluggable mechanism,we enhance the Fabric architecture with the national encryption *** addition,we research key technologies involved in the secure application protocol based on the *** propose a blockchain-based identity authentication protocol,detailing the design of an identity authentication scheme based on blockchain certificates and Fabric CA,and use a dual-signature method to further improve its security and ***,we propose a flexible,dynamically configurable real-time access control and security audit mechanism based on blockchain,further enhancing the security of the system.

关键词： access control authentication Hyperledger Fabric security audit state secret algorithm

来源：评论

学校读者我要写书评

暂无评论

Mechanical Properties of Bellows Joint-Connected Buried Pipelines Subjected to Normal Fault: Parametric Analysis

引用

Journal of Pipeline Systems Engineering and Practice 2025年第3期16卷

作者： Lv, Yang Zhang, Xue-Jie Zhou, Hong-Yuan Li, Fang-Fang Tianjin Key Laboratory of Civil Structure Protection and Reinforcement Tianjin Chengjian Univ. 26 Jinjing Rd. Xiqing Tianjin300384 China Key Laboratory of Urban Security and Disaster Engineering of Ministry of Education Beijing Univ. of Technology Beijing100124 China

Buried pipelines that cross normal faults are at risk of damage because of insufficient deformation capacity. Bellows joints have been proven to have the potential to significantly increase the deformation capacity of the pipelines;however, the geometric parameters of bellows joints are crucial in determining the performance of buried pipelines under normal fault. In this study, mechanical tests of a buried steel pipeline with a two-convolution bellows joint were conducted first. A finite element model (FEM) was developed in ABAQUS software and verified using the test results. The impacts of convolution number, radius, and spacing of the bellows joints in the buried steel pipelines were then analyzed based on the validated FEM. The numerical results indicate that the bellows joint can effectively withstand ground deformation caused by normal faults. Increasing the number of convolutions, employing a larger convolution radius, and maintaining a certain convolution spacing can enhance the deformation and energy absorption capacity of bellows joints. © 2025 American Society of Civil Engineers.

关键词： ABAQUS

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：