Is it secure to measure the reliability of local models by similarity in federated learning (FL)? This paper delves into an unexplored security threat concerning applying similarity metrics, such as the L_2 norm, Euclidean distance, and cosine similarity, in protecting FL. We first uncover the deficiencies of similarity metrics that high-dimensional local models, including benign and poisoned models, may be evaluated to have the same similarity while being significantly different in the parameter values. We then leverage this finding to devise a novel untargeted model poisoning attack, Faker, which launches the attack by simultaneously maximizing the evaluated similarity of the poisoned local model and the difference in the parameter values. Experimental results based on seven datasets and eight defenses show that Faker outperforms the state-of-the-art benchmark attacks by 1.1-9.0X in reducing accuracy and 1.2-8.0X in saving time cost, which even holds for the case of a single malicious client with limited knowledge about the FL system. Moreover, Faker can degrade the performance of the global model by attacking only once. We also preliminarily explore extending Faker to other attacks, such as backdoor attacks and Sybil attacks. Lastly, we provide a model evaluation strategy, called the similarity of partial parameters (SPP), to defend against Faker. Given that numerous mechanisms in FL utilize similarity metrics to assess local models, this work suggests that we should be vigilant regarding the potential risks of using these metrics.
TrustChain: A Blockchain Framework for Auditing and Verifying Aggregators in Decentralized Federated Learning
Department of Electrical and Computer Engineering, University of Windsor（威省大学电气与计算机工程系）；Faculty of Computer Science, University of New Brunswick（新不伦瑞克大学计算机科学学院）
Federated learning is an emerging privacy-preserving AI technique where clients (i.e., organisations or devices) train models locally and formulate a global model based on the local model updates without transferring local data externally. However, federated learning systems struggle to achieve trustworthiness and embody responsible AI principles. In particular, federated learning systems face accountability and fairness challenges due to multi-stakeholder involvement and heterogeneity in client data distribution. To enhance the accountability and fairness of federated learning systems, we pre…
The Chinese University of Hong Kong（香港中文大学）；University of Electronic Science and Technology of China（电子科技大学）；Peng Cheng Lab（鹏城实验室）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））
Trustworthy artificial intelligence (AI) technology has revolutionized daily life and greatly benefited human society. Among various AI technologies, Federated Learning (FL) stands out as a promising solution for diverse real-world scenarios, ranging from risk evaluation systems in finance to cutting-edge technologies like drug discovery in life sciences. However, challenges around data isolation and privacy threaten the trustworthiness of FL systems. Adversarial attacks against data privacy, learning algorithm stability, and system confidentiality are particularly concerning in the context of…
Hong Kong University of Science & Technology（香港科技大学）
In federated learning, multiple parties collaborate in order to train a global model over their respective datasets. Even though cryptographic primitives (e.g., homomorphic encryption) can help achieve data privacy in this setting, some partial information may still be leaked across parties if this is done non-judiciously. In this work, we study the federated learning framework of SecureBoost [Cheng et al., FL@IJCAI'19] as a specific such example, demonstrate a leakage-abuse attack based on its leakage profile, and experimentally evaluate the effectiveness of our attack. We then propose two se…
State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications（网络与交换技术国家重点实验室，北京邮电大学）；School of Computer Science and Engineering, Nanyang Technological University（南洋理工大学计算机科学与工程学院）；The Future Network of Intelligence Institute, The Chinese University of Hong Kong (Shenzhen)（香港中文大学（深圳）未来智联网络研究院）；School of Science and Engineering, The Chinese University of Hong Kong (Shenzhen)（香港中文大学（深圳）理工学院）
Agentic Trust Coordination for Federated Learning through Adaptive Thresholding and Autonomous Decision Making in Sustainable and Resilient Industrial Networks
London South Bank University（伦敦南岸大学）；Instituto de Telecomunicações（电信研究所）
Peking University（北京大学）；Renmin University of China（中国人民大学）；Shanghai AI Lab（上海人工智能实验室）；Tencent Inc.（腾讯公司）；Tsinghua University（清华大学）
Federated Learning has become a widely-used framework which allows learning a global model on decentralized local datasets under the condition of protecting local data privacy. However, federated learning faces severe optimization difficulty when training samples are not independently and identically distributed (non-i.i.d.). In this paper, we point out that the client sampling practice plays a decisive role in the aforementioned optimization difficulty. We find that the negative client sampling will cause the merged data distribution of currently sampled clients heavily inconsistent with that…
University of Southern California（南加州大学）；WeBank（微众银行）；University of Rochester（罗切斯特大学）；University of Michigan（密歇根大学）；Kwai Inc.（快手公司）
Federated learning has become increasingly important for modern machine learning, especially for data privacy-sensitive scenarios. Existing federated learning mostly adopts the central server-based architecture or centralized architecture. However, in many social network scenarios, centralized federated learning is not applicable (e.g., a central agent or server connecting all users may not exist, or the communication cost to the central server is not affordable). In this paper, we consider a generic setting: 1) the central server may not exist, and 2) the social network is unidirectional or o…
Trustworthy Blockchain-based Federated Learning for Electronic Health Records: Securing Participant Identity with Decentralized Identifiers and Verifiable Credentials
Federal Institute of Education, Science, and Technology of Rio Grande do Norte (IFRN)（里约格兰德北教育科学和技术联邦学院）
iSING Lab, Hong Kong University of Science and Technology（香港科技大学iSING实验室）；Clustar Technology Co., Ltd.（星云科技股份有限公司）；Peng Cheng Lab（鹏城实验室）
Vertical federated learning (VFL) leverages various privacy-preserving algorithms, e.g., homomorphic encryption or secret sharing based SecureBoost, to ensure data privacy. However, these algorithms all require a semi-honest secure definition, which raises concerns in real-world applications. In this paper, we present Aegis, a trusted, automatic, and accurate verification framework to verify the security of VFL jobs. Aegis is separated from local parties to ensure the security of the framework. Furthermore, it automatically adapts to evolving VFL algorithms by defining the VFL job as a finite …
Imperial College London（帝国理工学院）；Telefónica Research（西班牙电信研究院）
We propose and implement a Privacy-preserving Federated Learning ($PPFL$) framework for mobile systems to limit privacy leakages in federated learning. Leveraging the widespread presence of Trusted Execution Environments (TEEs) in high-end and mobile devices, we utilize TEEs on clients for local training, and on servers for secure aggregation, so that model/gradient updates are hidden from adversaries. Challenged by the limited memory size of current TEEs, we leverage greedy layer-wise training to train each model's layer inside the trusted area until its convergence. The performance evaluatio…
ZTFed-MAS2S: A Zero-Trust Federated Learning Framework with Verifiable Privacy and Trust-Aware Aggregation for Wind Power Data Imputation
School of Electrical Engineering, Northeast Electric Power University（电气工程学院，东北电力大学）；School of Artificial Intelligence and Automation, Huazhong University of Science and Technology（人工智能与自动化学院，华中科技大学）；State Grid Xiamen Electric Power Supply Company（国家电网厦门供电有限公司）；Department of Electrical Engineering, City University of Hong Kong（电气工程系，香港城市大学）
A common privacy issue in traditional machine learning is that data needs to be disclosed for the training procedures. In situations with highly sensitive data such as healthcare records, accessing this information is challenging and often prohibited. Luckily, privacy-preserving technologies have been developed to overcome this hurdle by distributing the computation of the training and ensuring the data privacy to their owners. The distribution of the computation to multiple participating entities introduces new privacy complications and risks. In this paper, we present a privacy-preserving de…
Enabling Trustworthy Federated Learning in Industrial IoT: Bridging the Gap Between Interpretability and Robustness
Mepco Schlenk Engineering College（梅普科施伦克工程学院）；Fordham University（福特汉姆大学）；University of South Florida（南佛罗里达大学）；Hung Yen University of Technology and Education（兴安工业大学）；Royal Military College of Canada（加拿大皇家军事学院）
Enhancing Mutual Trustworthiness in Federated Learning for Data-Rich Smart Cities
Mohammad Bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Polytechnique Montréal（蒙特利尔理工学院）；Lebanese American University（黎巴嫩美国大学）；Khalifa University（哈利法大学）；New York University（纽约大学）；Technology Innovation Institute (TII)（技术创新研究所）
Shanghai Jiao Tong University（上海交通大学）；Hangzhou Normal University（杭州师范大学）；Shanghai Normal University（上海师范大学）
Federated learning (FL) provides an emerging approach for collaboratively training semantic encoder/decoder models of semantic communication systems, without private user data leaving the devices. Most existing studies on trustworthy FL aim to eliminate data poisoning threats that are produced by malicious clients, but in many cases, eliminating model poisoning attacks brought by fake servers is also an important objective. In this paper, a certificateless authentication-based trustworthy federated learning (CATFL) framework is proposed, which mutually authenticates the identity of clients and…
A Trust-Network-Based Federated Learning Framework for Multi-Center Aging Clock Prediction
PolyU Academy for Artificial Intelligence, The Hong Kong Polytechnic University（香港理工大学人工智能研究院）；Quantum Life；Department of Computing, The Hong Kong Polytechnic University（香港理工大学计算学系）；Kyoto University（京都大学）；Jilin University（吉林大学）
Université de Sherbrooke（舍布鲁克大学）；GREYC CNRS（法国国家科学研究中心灰西实验室）；ENSICAEN（法国国立卡昂高等工程师学院）；Normandie University（诺曼底大学）；University of Technology of Troyes（特鲁瓦技术大学）
Federated learning (FL) is a distributed machine learning (ML) technique that enables collaborative training in which devices perform learning using a local dataset while preserving their privacy. This technique ensures privacy, communication efficiency, and resource conservation. Despite these advantages, FL still suffers from several challenges related to reliability (i.e., unreliable participating devices in training), tractability (i.e., a large number of trained models), and anonymity. To address these issues, we propose a secure and trustworthy blockchain framework (SRB-FL) tailored to F…
Cost-TrustFL: Cost-Aware Hierarchical Federated Learning with Lightweight Reputation Evaluation across Multi-Cloud
Westcliff University（韦斯特克莱夫大学）；University of Virginia（弗吉尼亚大学）；University of Washington（华盛顿大学）；Northeastern University（东北大学）；University of Michigan（密歇根大学）
A Trustworthy AIoT-enabled Localization System via Federated Learning and Blockchain
School of Electrical and Electronics Engineering, Nanyang Technological University（南洋理工大学电气与电子工程学院）；Chainbase Inc.（Chainbase公司）；PublicAI Inc.（PublicAI公司）
Federated learning is a learning paradigm to enable collaborative learning across different parties without revealing raw data. Notably, vertical federated learning (VFL), where parties share the same set of samples but only hold partial features, has a wide range of real-world applications. However, most existing studies in VFL disregard the "record linkage" process. They design algorithms either assuming the data from different parties can be exactly linked or simply linking each record with its most similar neighboring record. These approaches may fail to capture the key features from other…
Robust Federated Learning under Adversarial Attacks via Loss-Based Client Clustering
School of Electrical and Computer Engineering, National Technical University of Athens（电气与计算机工程学院，国家技术大学雅典）；Faculty of Sciences, University of Novi Sad（科学学院，诺维萨德大学）
Blockchain-Empowered Cyber-Secure Federated Learning for Trustworthy Edge Computing
Knight Foundation School of Computing and Information Sciences, Florida International University (FIU)（佛罗里达国际大学奈特基金会计算与信息科学学院）；School of Computing, Southern Illinois University（南伊利诺伊大学计算学院）；Enterprise and Logistics Engineering program at FIU（佛罗里达国际大学企业与物流工程项目）
GuardFed: A Trustworthy Federated Learning Framework Against Dual-Facet Attacks
School of Artificial Intelligence and Computer Science, Nantong University（人工智能与计算机科学学院，南通大学）；School of Electrical and Computer Engineering, The University of Sydney（电气与计算机工程学院，悉尼大学）；School of Computer Science, University of St Andrews（计算机科学学院，圣安德鲁斯大学）；Faculty of Data Science, City University of Macau（数据科学学院，澳门城市大学）；Department of Electrical and Computer Engineering, University of Alberta（电气与计算机工程学院，阿尔伯塔大学）
FedFiTS: Fitness-Selected, Slotted Client Scheduling for Trustworthy Federated Learning in Healthcare AI
Department of Computer Science University of the Western Cape（计算机科学系，西开普敦大学）；Department of Computer Science Missouri University of Science and Technology（计算机科学系，密苏里科学与技术大学）
