With the increased attention and legislation for data-privacy, collaborative machine learning (ML) algorithms are being developed to ensure the protection of private data used for processing. Federated learning (FL) is the most popular of these methods, which provides privacy preservation by facilitating collaborative training of a shared model without the need to exchange any private data with a centralized server. Rather, an abstraction of the data in the form of a machine learning model update is sent. Recent studies showed that such model updates may still very well leak private information and thus more structured risk assessment is needed. In this paper, we analyze existing vulnerabilities of FL and subsequently perform a literature review of the possible attack methods targetingFL privacy protection capabilities. These attack methods are then categorized by a basic taxonomy. Additionally, we provide a literature study of the most recent defensive strategies and algorithms for FL aimed to overcome these attacks. These defensive strategies are categorized by their respective underlying defence principle. The paper concludes that the application of a single defensive strategy is not enough to provide adequate protection to all available attack methods.
AdaBFL: Multi-Layer Defensive Adaptive Aggregation for Bzantine-Robust Federated Learning
College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics（南京航空航天大学计算机科学与技术学院）；MIIT Key Laboratory of Pattern Analysis and Machine Intelligence（信息产业部模式分析与机器智能重点实验室）
Nanjing University of Science and Technology（南京理工大学）；National Research Tomsk Polytechnic University（托木斯克国立研究理工大学）；Data61, CSIRO（联邦科学与工业研究组织Data61）；Pohang University of Science and Technology (POSTECH)（浦项科技大学）；Princeton University（普林斯顿大学）
Federated learning (FL), as a type of distributed machine learning frameworks, is vulnerable to external attacks on FL models during parameters transmissions. An attacker in FL may control a number of participant clients, and purposely craft the uploaded model parameters to manipulate system outputs, namely, model poisoning (MP). In this paper, we aim to propose effective MP algorithms to combat state-of-the-art defensive aggregation mechanisms (e.g., Krum and Trimmed mean) implemented at the server without being noticed, i.e., covert MP (CMP). Specifically, we first formulate the MP as an opt…
Nanjing University of Science and Technology（南京理工大学）；Data61, CSIRO（联邦科学与工业研究组织数据61研究所）；Shanghai Jiao Tong University（上海交通大学）；Princeton University（普林斯顿大学）
Owing to the low communication costs and privacy-promoting capabilities, Federated Learning (FL) has become a promising tool for training effective machine learning models among distributed clients. However, with the distributed architecture, low quality models could be uploaded to the aggregator server by unreliable clients, leading to a degradation or even a collapse of training. In this paper, we model these unreliable behaviors of clients and propose a defensive mechanism to mitigate such a security risk. Specifically, we first investigate the impact on the models caused by unreliable clie…
Crossing Roads of Federated Learning and Smart Grids: Overview, Challenges, and Perspectives
University of Applied Sciences（应用科学大学）；University of Skikda（斯基克达大学）；University of Dubai（迪拜大学）；University of Sharjah（沙迦大学）；De Montfort University（德蒙福特大学）；Qatar University（卡塔尔大学）；University of Klagenfurt（克拉根福大学）
Federated learning holds great promise in learning from fragmented sensitive data and has revolutionized how machine learning models are trained. This article provides a systematic overview and detailed taxonomy of federated learning. We investigate the existing security challenges in federated learning and provide a comprehensive overview of established defense techniques for data poisoning, inference attacks, and model poisoning attacks. The work also presents an overview of current training challenges for federated learning, focusing on handling non-i.i.d. data, high dimensionality issues, …
Recent studies have shown that federated learning (FL) is vulnerable to poisoning attacks that inject a backdoor into the global model. These attacks are effective even when performed by a single client, and undetectable by most existing defensive techniques. In this paper, we propose Backdoor detection via Feedback-based Federated Learning (BAFFLE), a novel defense to secure FL against backdoor attacks. The core idea behind BAFFLE is to leverage data of multiple clients not only for training but also for uncovering model poisoning. We exploit the availability of diverse datasets at the variou…
Carnegie Mellon University（卡内基梅隆大学）；Bosch Center for Artificial Intelligence（博世人工智能中心）；Determined AI
Federated learning involves training statistical models over remote devices or siloed data centers, such as mobile phones or hospitals, while keeping data localized. Training in heterogeneous and potentially massive networks introduces novel challenges that require a fundamental departure from standard approaches for large-scale machine learning, distributed optimization, and privacy-preserving data analysis. In this article, we discuss the unique characteristics and challenges of federated learning, provide a broad overview of current approaches, and outline several directions of future work …
A Comprehensive Data-centric Overview of Federated Graph Learning
Beijing Institute of Technology（北京理工大学）；Sun Yat-sen University（中山大学）；Peking University（北京大学）；Institute of Information Science, Beijing Jiaotong University（北京交通大学信息科学学院）；Computer Network Information Center, Chinese Academy of Sciences（中国科学院计算机网络信息中心）
Federated learning (FL) is an emerging technology that enables the training of machine learning models from multiple clients while keeping the data distributed and private. Based on the participating clients and the model training scale, federated learning can be classified into two types: cross-device FL where clients are typically mobile devices and the client number can reach up to a scale of millions; cross-silo FL where clients are organizations or companies and the client number is usually small (e.g., within a hundred). While existing studies mainly focus on cross-device FL, this paper …
Refiner: Data Refining against Gradient Leakage Attacks in Federated Learning
East China Normal University（东华师范大学）；The State Key Laboratory of Blockchain and Data Security, Zhejiang University（浙江大学区块链与数据安全国家重点实验室）；Alibaba Group（阿里巴巴集团）
Exploring Machine Learning Models for Federated Learning: A Review of Approaches, Performance, and Limitations
Data Science and Analytics Institute, University of Oklahoma（俄克拉荷马大学数据科学与分析学院）；School of Industrial and Systems Engineering, University of Oklahoma（俄克拉荷马大学工业与系统工程学院）；Isfahan University of Technology（伊斯法罕理工大学）
Differentially Private Federated Learning: A Systematic Review
Stevens Institute of Technology（史蒂文斯理工学院）；University of Connecticut（康涅狄格大学）；Tongji University（同济大学）；Northeastern University（东北大学）；The Hong Kong Polytechnic University（香港理工大学）；East China Normal University（华东师范大学）；Institute of Science Tokyo（东京科学研究所）
Decentralized Federated Learning: A Survey on Security and Privacy
University of Windsor（温莎大学）；University of New Brunswick（新不伦瑞克大学）；University of Western Ontario（西安大略大学）；Hong Kong University of Science and Technology（香港科技大学）；WeBank（微众银行）
Poisoning Attacks on Federated Learning for Autonomous Driving
Umeå University（于默奥大学）；AI Sweden（瑞典人工智能研究院）；Royal Institute of Technology（皇家理工学院）；Chalmers University of Technology（查尔姆斯理工大学）；Dakota State University（达科他州立大学）；Scaleout Systems（Scaleout系统公司）
University of Applied Science Würzburg-Schweinfurt（维尔茨堡-施韦因富特应用科学大学）；CEREMADE University Paris Dauphine PSL（巴黎多芬大学PSL CEREMADE）
In recent years the applications of machine learning models have increased rapidly, due to the large amount of available data and technological progress.While some domains like web analysis can benefit from this with only minor restrictions, other fields like in medicine with patient data are strongerregulated. In particular \emph{data privacy} plays an important role as recently highlighted by the trustworthy AI initiative of the EU or general privacy regulations in legislation. Another major challenge is, that the required training \emph{data is} often \emph{distributed} in terms of features…
FedCG: Leverage Conditional GAN for Protecting Privacy and Maintaining Competitive Performance in Federated Learning
AI Group, WeBank（微众银行人工智能部）；School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机科学与工程学院）；Department of CSE, Hong Kong University of Science and Technology（香港科技大学计算机科学与工程系）
Beijing University of Posts and Telecommunications（北京邮电大学）
Federated learning has emerged as an effective paradigm to achieve privacy-preserving collaborative learning among different parties. Compared to traditional centralized learning that requires collecting data from each party, in federated learning, only the locally trained models or computed gradients are exchanged, without exposing any data information. As a result, it is able to protect privacy to some extent. In recent years, federated learning has become more and more prevalent and there have been many surveys for summarizing related methods in this hot research topic. However, most of the…
Since the federated learning, which makes AI learning possible without moving local data around, was introduced by google in 2017 it has been actively studied particularly in the field of medicine. In fact, the idea of machine learning in AI without collecting data from local clients is very attractive because data remain in local sites. However, federated learning techniques still have various open issues due to its own characteristics such as non identical distribution, client participation management, and vulnerable environments. In this presentation, the current issues to make federated le…
We describe a threat model under which a split network-based federated learning system is susceptible to a model inversion attack by a malicious computational server. We demonstrate that the attack can be successfully performed with limited knowledge of the data distribution by the attacker. We propose a simple additive noise method to defend against model inversion, finding that the method can significantly reduce attack efficacy at an acceptable accuracy trade-off on MNIST. Furthermore, we show that NoPeekNN, an existing defensive method, protects different information from exposure, suggest…
Federated learning (FL) is a popular distributed learning framework that trains a global model through iterative communications between a central server and edge devices. Recent works have demonstrated that FL is vulnerable to model poisoning attacks. Several server-based defense approaches (e.g. robust aggregation), have been proposed to mitigate such attacks. However, we empirically show that under extremely strong attacks, these defensive methods fail to guarantee the robustness of FL. More importantly, we observe that as long as the global model is polluted, the impact of attacks on the gl…
Vellore Institute of Technology（韦洛尔理工学院）；Charles Darwin University（查尔斯达尔文大学）；Stockholm University（斯德哥尔摩大学）；Chaitanya Bharathi Institute of Technology（柴塔尼亚巴拉蒂理工学院）
Internet of Underwater Things (IoUT) have gained rapid momentum over the past decade with applications spanning from environmental monitoring and exploration, defence applications, etc. The traditional IoUT systems use machine learning (ML) approaches which cater the needs of reliability, efficiency and timeliness. However, an extensive review of the various studies conducted highlight the significance of data privacy and security in IoUT frameworks as a predominant factor in achieving desired outcomes in mission critical applications. Federated learning (FL) is a secured, decentralized framew…
Federated Large Language Models: Current Progress and Future Directions
Carnegie Mellon University（卡内基梅隆大学）；Duke University（杜克大学）；University of California San Diego（加州大学圣地亚哥分校）；The University of New South Wales（新南威尔士大学）；Adobe Research（Adobe研究）；University of Maryland College Park（马里兰大学学院公园分校）；CSIRO’s Data61（澳大利亚联邦科学与工业研究组织Data61）
Centre Tecnològic de Telecomunicacions de Catalunya（加泰罗尼亚电信技术中心）；Nokia Bell-Labs（诺基亚贝尔实验室）
Federated learning is one of the most appealing alternatives to the standard centralized learning paradigm, allowing a heterogeneous set of devices to train a machine learning model without sharing their raw data. However, it requires a central server to coordinate the learning process, thus introducing potential scalability and security issues. In the literature, server-less federated learning approaches like gossip federated learning and blockchain-enabled federated learning have been proposed to mitigate these issues. In this work, we propose a complete overview of these three techniques pr…
Vertical Federated Learning for Effectiveness, Security, Applicability: A Survey
The National Engineering Research Center for Multimedia Software（国家多媒体软件工程技术研究中心）；School of Computer Science, Wuhan University（武汉大学计算机学院）；United Institute of Informatics Problems of Belarus National Academy of Sciences（白俄罗斯国家科学院信息问题联合研究所）；National Academy of Sciences of Belarus（白俄罗斯国家科学院）；Department of Computer Science, Hong Kong Baptist University（香港浸会大学计算机系）
University of Technology Sydney（悉尼科技大学）；Macquarie University（麦考瑞大学）；University of New Castle（纽卡斯尔大学）；University of Porto（波尔图大学）；Nanyang Technological University（南洋理工大学）；University of Minnesota（明尼苏达大学）
Edge Intelligence Over the Air: Two Faces of Interference in Federated Learning
Singapore University of Technology and Design（新加坡科技设计大学）；Kyung Hee University（庆熙大学）；Zhejiang University/University of Illinois Urbana-Champaign Institute（浙江大学伊利诺伊大学厄巴纳香槟校区联合学院）；Zhejiang University（浙江大学）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
CTTC（加泰罗尼亚电信技术中心）；Trinity College Dublin（都柏林圣三一学院）；Imperial College London（伦敦帝国理工学院）；New York University（纽约大学）；University of Modena and Reggio Emilia（摩德纳和雷焦艾米利亚大学）；Xiamen University（厦门大学）；Universitat Pompeu Fabra（庞培法布拉大学）
As wireless standards evolve, more complex functionalities are introduced to address the increasing requirements in terms of throughput, latency, security, and efficiency. To unleash the potential of such new features, artificial intelligence (AI) and machine learning (ML) are currently being exploited for deriving models and protocols from data, rather than by hand-programming. In this paper, we explore the feasibility of applying ML in next-generation wireless local area networks (WLANs). More specifically, we focus on the IEEE 802.11ax spatial reuse (SR) problem and predict its performance …
Shadow defense against gradient inversion attack in federated learning
Bioengineering Department, Imperial College London, London W12 0BZ, UK；School of Computer Engineering；Science, Shanghai university, Shanghai 200444, China；Bioengineering Department；Imperial-X, Imperial College London, London W12 7SL, UK；Lung Institute, Imperial College London, London SW7 2AZ, UK；Cardiovascular Research Centre, Royal Brompton Hospital, London SW3 6NP, UK；School of Biomedical Engineering \& Imaging Sciences, King's College London, London WC2R 2LS, UK
A Survey of Personalized Federated Foundation Models for Privacy-Preserving Recommendation
Australian Artificial Intelligence Institute, University of Technology Sydney（澳大利亚人工智能研究所，悉尼技术大学）；College of Computer Science and Technology, Jilin University（吉林大学计算机科学与技术学院）；School of Computer Science and Technology, Beijing Jiaotong University（北京交通大学计算机科学与技术学院）；Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University（香港理工大学数据科学与人工智能系）
EPFL（洛桑联邦理工学院）；George Mason University（乔治梅森大学）；Institute of Applied Computing, CNR（意大利国家研究委员会应用计算研究所）
We investigate the security of Split Learning -- a novel collaborative machine learning framework that enables peak performance by requiring minimal resources consumption. In the present paper, we expose vulnerabilities of the protocol and demonstrate its inherent insecurity by introducing general attack strategies targeting the reconstruction of clients' private training sets. More prominently, we show that a malicious server can actively hijack the learning process of the distributed model and bring it into an insecure state that enables inference attacks on clients' data. We implement diffe…
Southern University of Science and Technology（南方科技大学）
Federated learning (FL) has been proposed to protect data privacy and virtually assemble the isolated data silos by cooperatively training models among organizations without breaching privacy and security. However, FL faces heterogeneity from various aspects, including data space, statistical, and system heterogeneity. For example, collaborative organizations without conflict of interest often come from different areas and have heterogeneous data from different feature spaces. Participants may also want to train heterogeneous personalized local models due to non-IID and imbalanced data distrib…
A Comprehensive Survey On Client Selections in Federated Learning
College of Computing and Information Technology, University of Doha for Science and Technology（多哈科技大学计算与信息技术学院）；Electrical Engineering, Qatar University（卡塔尔大学电气工程系）
Multimodal Federated Learning in Healthcare: a Review
West Virginia University（西弗吉尼亚大学）；Tribhuvan University（特里布万大学）；University at Albany（奥尔巴尼大学）；University of Pittsburgh（匹兹堡大学）；University of Aberdeen（阿伯丁大学）
Vellore Institute of Technology（韦洛尔理工学院）；University of Nantes（南特大学）
The rapid development of the Internet and smart devices trigger surge in network traffic making its infrastructure more complex and heterogeneous. The predominated usage of mobile phones, wearable devices and autonomous vehicles are examples of distributed networks which generate huge amount of data each and every day. The computational power of these devices have also seen steady progression which has created the need to transmit information, store data locally and drive network computations towards edge devices. Intrusion detection systems play a significant role in ensuring security and pri…
