Malicious Client

Malicious client attacks in federated learning and other distributed systems pose a significant threat by compromising model integrity and data privacy. Current research focuses on developing robust aggregation methods, such as Bayesian approaches and those leveraging graph clustering or time series analysis, to identify and mitigate the influence of malicious clients, even in the presence of large-scale or sophisticated attacks like backdooring. These efforts are crucial for ensuring the security and reliability of federated learning, a technology with broad applications in areas like healthcare and IoT, where data decentralization is paramount. The development of provably secure frameworks and efficient recovery mechanisms remains a key area of ongoing investigation.

Papers

August 20, 2024

ETGuard: Malicious Encrypted Traffic Detection in Blockchain-based Power Grid Systems
Peng Zhou, Yongdong Liu, Lixun Ma, Weiye Zhang, Haohan Tan, Zhenguang Liu, Butian Huang
Smart Grid Malicious Client Encrypted Traffic Encrypted Traffic Classification

July 9, 2024

Tracing Back the Malicious Clients in Poisoning Attacks to Federated Learning
Yuqi Jia, Minghong Fang, Hongbin Liu, Jinghuai Zhang, Neil Zhenqiang Gong
Poisoning Attack Malicious Client Training Time Attack

May 1, 2024

Trust Driven On-Demand Scheme for Client Deployment in Federated Learning
Mario Chahoud, Azzam Mourad, Hadi Otrok, Jamal Bentahar, Mohsen Guizani
Federated Learning Malicious Client Trust Mechanism

March 10, 2024

Fake or Compromised? Making Sense of Malicious Clients in Federated Learning
Hamid Mozaffari, Sunav Choudhary, Amir Houmansadr
Federated Learning Fake Speech Multiple Sens Malicious Client Adversary Model Aggregation Defense

January 16, 2024

Towards Efficient and Certified Recovery from Poisoning Attacks in Federated Learning
Yu Jiang, Jiyuan Shen, Ziyao Liu, Chee Wei Tan, Kwok-Yan Lam
High Efficiency Poisoning Attack Malicious Client Recovery Guarantee Optimal Recovery

January 10, 2024

Federated Unlearning: A Survey on Methods, Design Guidelines, and Evaluation Metrics
Nicolò Romandini, Alessio Mora, Carlo Mazzocca, Rebecca Montanari, Paolo Bellavista
Timely Survey NCD Method Evaluation Metric Learned Model Federated Unlearning Malicious Client General Data Protection Regulation Design Consideration

December 28, 2023

Securing NextG Systems against Poisoning Attacks on Federated Learning: A Game-Theoretic Solution
Yalin E. Sagduyu, Tugba Erpek, Yi Shi
Poisoning Attack Game Theoretic Signal Classification Malicious Client DEfense Mechanism NextG Wireless Network

December 4, 2023

FedBayes: A Zero-Trust Federated Learning Aggregation to Defend Against Adversarial Attacks
Marc Vucovich, Devin Quinn, Kevin Choi, Christopher Redino, Abdul Rahman, Edward Bowen
Adversarial Attack Federated Learning Data Poisoning Attack Malicious Client Label Flipping Attack

November 27, 2023

A Survey on Vulnerability of Federated Learning: A Learning Algorithm Perspective
Xianghua Xie, Chen Hu, Hanchi Ren, Jingjing Deng
Timely Survey Learning Algorithm Threat Model Latent Vulnerability Malicious Client Malicious Attack Composite Attack

November 17, 2023

FedTruth: Byzantine-Robust and Backdoor-Resilient Federated Learning Framework
Sheldon C. Ebron, Kan Yang
Federated Learning Byzantine Robust Robust Defense Model Poisoning Attack Malicious Client

October 25, 2023

Robust and Actively Secure Serverless Collaborative Learning
Olive Franzese, Adam Dziedzic, Christopher A. Choquette-Choo, Mark R. Thomas, Muhammad Ahmad Kaleem, Stephan Rabanser, Congyu Fang, Somesh Jha, Nicolas Papernot, Xiao Wang
Robust Version Collaborative Machine Learning Malicious Client Robust Aggregation

July 29, 2023

You Can Backdoor Personalized Federated Learning
Tiandi Ye, Cen Chen, Yinggui Wang, Xiang Li, Ming Gao
Backdoor Attack Malicious Client Step Attack pFL Method Decoupling Degradation

July 2, 2023

FedDefender: Backdoor Attack Defense in Federated Learning
Waris Gill, Ali Anwar, Muhammad Ali Gulzar
Malicious Client DEfense Mechanism Mitigating Backdoor Differential Testing

June 8, 2023

G$^2$uardFL: Safeguarding Federated Learning Against Backdoor Attacks through Attributed Client Graph Clustering
Hao Yu, Chuan Ma, Meng Liu, Tianyu Du, Ming Ding, Tao Xiang, Shouling Ji, Xinwang Liu
Backdoor Attack Graph Clustering State of the Art Defense Malicious Client

May 9, 2023

FedGT: Identification of Malicious Clients in Federated Learning with Secure Aggregation
Marvin Xhemrishi, Johan Östman, Antonia Wachter-Zeh, Alexandre Graell i Amat
Person Identification Secure Aggregation Malicious Client Private Aggregation

April 25, 2023

Chameleon: Adapting to Peer Images for Planting Durable Backdoors in Federated Learning
Yanbo Dai, Songze Li
Backdoor Attack Peer Agent Pace Adaptive Malicious Client Resilient Backdoor

March 29, 2023

Protecting Federated Learning from Extreme Model Poisoning Attacks via Multidimensional Time Series Anomaly Detection
Edoardo Gabrielli, Dimitri Belli, Vittorio Miori, Gabriele Tolomei
Native Robustness Multivariate Time Series Anomaly Detection Model Poisoning Attack Aggregation Function Malicious Client

December 5, 2022

FedCC: Robust Federated Learning against Model Poisoning Attacks
Hyejun Jeong, Hamin Son, Seohu Lee, Jayun Hyun, Tai-Myoung Chung
Model Poisoning Attack Malicious Client

October 20, 2022

FedRecover: Recovering from Poisoning Attacks in Federated Learning using Historical Information
Xiaoyu Cao, Jinyuan Jia, Zaixi Zhang, Neil Zhenqiang Gong
Federated Learning Poisoning Attack Historical Text Malicious Client Malicious Model

October 2, 2022

FLCert: Provably Secure Federated Learning against Poisoning Attacks
Xiaoyu Cao, Zaixi Zhang, Jinyuan Jia, Neil Zhenqiang Gong
Poisoning Attack Byzantine Robust Malicious Client

Malicious Client

Papers

ETGuard: Malicious Encrypted Traffic Detection in Blockchain-based Power Grid Systems

Tracing Back the Malicious Clients in Poisoning Attacks to Federated Learning

Trust Driven On-Demand Scheme for Client Deployment in Federated Learning

Fake or Compromised? Making Sense of Malicious Clients in Federated Learning

Towards Efficient and Certified Recovery from Poisoning Attacks in Federated Learning

Federated Unlearning: A Survey on Methods, Design Guidelines, and Evaluation Metrics

Securing NextG Systems against Poisoning Attacks on Federated Learning: A Game-Theoretic Solution

FedBayes: A Zero-Trust Federated Learning Aggregation to Defend Against Adversarial Attacks

A Survey on Vulnerability of Federated Learning: A Learning Algorithm Perspective

FedTruth: Byzantine-Robust and Backdoor-Resilient Federated Learning Framework

Robust and Actively Secure Serverless Collaborative Learning

You Can Backdoor Personalized Federated Learning

FedDefender: Backdoor Attack Defense in Federated Learning

G$^2$uardFL: Safeguarding Federated Learning Against Backdoor Attacks through Attributed Client Graph Clustering

FedGT: Identification of Malicious Clients in Federated Learning with Secure Aggregation

Chameleon: Adapting to Peer Images for Planting Durable Backdoors in Federated Learning

Protecting Federated Learning from Extreme Model Poisoning Attacks via Multidimensional Time Series Anomaly Detection

FedCC: Robust Federated Learning against Model Poisoning Attacks

FedRecover: Recovering from Poisoning Attacks in Federated Learning using Historical Information

FLCert: Provably Secure Federated Learning against Poisoning Attacks