Model Poisoning Against Federated Model Adaptation with Chain of Bit-Flips
CEA-Leti, Mines Saint-Etienne, Equipe Commune SAS(CEA-莱蒂, Mines圣艾蒂安, 共同团队SAS);Univ. Grenoble Alpes, CEA-Leti(格勒诺布尔阿尔卑斯大学, CEA-莱蒂);Mines Saint-Etienne, CEA-Leti, Centre CMP, Equipe commune SAS(Mines圣艾蒂安, CEA-莱蒂, CMP中心, 共同团队SAS)
Bastien Vuillod, Kevin Hector, Pierre-Alain Moellic, Jean-Max Dutertre, Olivier Potin
Federated Learning (FL) allows a set of clients to collectively train a global model without sharing local training data. Giving the responsibility of the training to decentralized actors may lead to poisoning attacks: clients controlled by malicious third party potentially poison the training dataset to install a backdoor in neural networks. In FL, these backdoor attacks rely solely on algorithmic approach, however, recent advances in hardware faults threats (e.g, Rowhammer) have widen the overall attack surface. In the context of federated model adaptation, we introduce a novel category of backdoor attack against FL systems that relies on model poisoning based on hardware-fault attacks. More precisely, we propose a task-agnostic backdoor attack that is implanted during the FL training time by inducing hardware faults (bit-flips) in parameters of a single local model. The backdoor is crafted during a previous offline phase from the pretrained model initially used by the FL system. Our results show that a backdoor can be successfully applied on different type of models and datasets. Typically, with up to 10 faults per malicious client occurrence and 19 total occurrences on a ResNet-18 are enough to reach 94% of attack success rate. Finally, we discuss the practicality and the robustness of the attack potential defenses, while putting into perspective the practical constraints of Rowhammer, which is the preferred attack vector for this type of threats.
FIDELIS: Blockchain-Enabled Protection Against Poisoning Attacks in Federated Learning
Department of Computer Science Saint Mary's College of California(计算机科学系圣玛丽学院);Department of Computer Science North Carolina State University(计算机科学系北卡罗来纳州立大学);Department of Computer Science Boise State University(计算机科学系博伊州立大学)
FLCert: Provably Secure Federated Learning against Poisoning Attacks
Meta Platforms(Meta平台公司);University of Science and Technology of China(中国科学技术大学);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Duke University(杜克大学)
Data Poisoning Attacks on Federated Machine Learning
Shenyang Institute of Automation, Chinese Academy of Sciences(中国科学院沈阳自动化研究所);University of Chinese Academy of Sciences(中国科学院大学);University of Rochester(罗切斯特大学)
Unraveling the Connections between Privacy and Certified Robustness in Federated Learning Against Poisoning Attacks
University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-尚佩恩分校);IBM Research(IBM研究院);UC Berkeley(加州大学伯克利分校);Amazon Web Services(亚马逊云服务);Stanford University(斯坦福大学)
Leverage Variational Graph Representation For Model Poisoning on Federated Learning
University of Cambridge(剑桥大学);Real-Time and Embedded Computing Systems Research Centre (CISTER)(实时与嵌入式计算系统研究中心(CISTER));Carnegie Mellon University(卡内基梅隆大学);Commonwealth Scientific and Industrial Research Organization (CSIRO)(联邦科学与工业研究组织(CSIRO));TU Berlin(柏林工业大学);The University of Sydney(悉尼大学)
FedMID: A Data-Free Method for Using Intermediate Outputs as a Defense Mechanism Against Poisoning Attacks in Federated Learning
School of Computing, KAIST(韩国科学技术院计算机学院);Samsung Research(三星研究院);Data Science Group, Institute for Basic Science(基础科学研究院数据科学组);Max Planck Institute for Security and Privacy(马克斯·普朗克安全与隐私研究所)
SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning
Shanghai Jiao Tong University(上海交通大学);Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Tsinghua University(清华大学);Jinan University(暨南大学)
Data and Model Poisoning Backdoor Attacks on Wireless Federated Learning, and the Defense Mechanisms: A Comprehensive Survey
Deakin University(迪肯大学);Data61, CSIRO(澳大利亚联邦科学与工业研究组织数据61研究所);Qilu University of Technology (Shandong Academy of Sciences)(齐鲁工业大学(山东省科学院));University of Manitoba(曼尼托巴大学)
Protecting Federated Learning from Extreme Model Poisoning Attacks via Multidimensional Time Series Anomaly Detection
Department of Computer, Control and Management Engineering, Sapienza University of Rome(计算机、控制与管理工程系,罗马萨皮恩扎大学);National Research Council in Pisa(比萨国家研究理事会);Department of Statistics, Ludwig-Maximilians-University of Munich(统计学系,慕尼黑路德维希-马克西米利安大学);Department of Computer Science, Sapienza University of Rome(计算机科学系,罗马萨皮恩扎大学)
Enhanced Detective: A Dual-Stage Proactive Defense Against Internal Poisoning Attacks in Financial Fraud Detection Using Federated Learning
University of Bucharest(布加勒斯特大学);Luxembourg Institute of Science and Technology (LIST)(卢森堡科学与技术研究所);Research Institute of the University of Bucharest (ICUB)(布加勒斯特大学研究院)
Poisoning Attacks and Defenses to Federated Unlearning
ShanghaiTech University(上海科技大学);Xidian University(西安电子科技大学);North Carolina State University(北卡罗来纳州立大学);University of North Texas(北德克萨斯大学);University of Louisville(路易斯维尔大学)
PCDM: A Diffusion-Based Data Poisoning Attack Against Federated Learning Systems
Beijing Jiaotong University(北京交通大学);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);Tsinghua University(清华大学);Hong Kong University of Science and Technology(香港科技大学)
PPFPL: Cross-silo Privacy-preserving Federated Prototype Learning Against Data Poisoning Attacks
Qilu University of Technology(齐鲁工业大学);University of Electronic Science and Technology of China(电子科技大学);Big Data Institute, Qilu University of Technology(齐鲁工业大学大数据研究院);University of Science and Technology of China(中国科学技术大学);Cyber Security Institute, University of Science and Technology of China(中国科学技术大学网络空间安全学院);China University of Petroleum(中国石油大学)