Data to 14 Oct 2026

Learning to Detect Malicious Clients for Robust Federated Learning

arXiv 2002.00211 ↗First posted 1 Feb 2020cs.LG cs.CR stat.MLcited by 88

Not on the map. Why?

Abstract (arXiv)

Federated learning systems are vulnerable to attacks from malicious clients. As the central server in the system cannot govern the behaviors of the clients, a rogue client may initiate an attack by sending malicious model updates to the server, so as to degrade the learning performance or enforce targeted model poisoning attacks (a.k.a. backdoor attacks). Therefore, timely detecting these malicious model updates and the underlying attackers becomes critically important. In this work, we propose a new framework for robust federated learning where the central server learns to detect and remove the malicious model updates using a powerful detection model, leading to targeted defense. We evaluate our solution in both image classification and sentiment analysis tasks with a variety of machine learning models. Experimental results show that our solution ensures robust federated learning that is resilient to both the Byzantine attacks and the targeted model poisoning attacks.

Key facts. Cited by 88 papers in the map (data through 14 Oct 2026). First posted on arXiv 1 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 14; 2022: 15; 2023: 19; 2024: 16; 2025: 20; 2026: 4.

88 papers.

Sort:

By area:

2023Heterogeneous Federated Learning: State-of-the-art and Research Challengescited by 161
2022FLDetector: Defending Federated Learning Against Model Poisoning Attacks via Detecting Malicious Clientscited by 125
2022Neurotoxin: Durable Backdoors in Federated Learningcited by 98
2022Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challengescited by 84
2022DeepSight: Mitigating Backdoor Attacks in Federated Learning Through Deep Model Inspectioncited by 81
2023A Survey on Federated Unlearning: Challenges, Methods, and Future Directionscited by 63
2022FedRecover: Recovering from Poisoning Attacks in Federated Learning using Historical Informationcited by 58
2022FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learningcited by 37
2023Backdoor Attacks and Defenses in Federated Learning: Survey, Challenges and Future Research Directionscited by 33
2022LoMar: A Local Defense Against Poisoning Attack on Federated Learningcited by 31
2023Integration of Large Language Models and Federated Learningcited by 31
2024Decentralized Federated Learning: A Survey on Security and Privacycited by 25

38 more

2023A Survey of Trustworthy Federated Learning with Perspectives on Security, Robustness, and Privacycited by 24
2023BayBFed: Bayesian Backdoor Defense for Federated Learningcited by 23
2023Multi-metrics adaptively identifies backdoors in Federated learningcited by 23
2023Data and Model Poisoning Backdoor Attacks on Wireless Federated Learning, and the Defense Mechanisms: A Comprehensive Surveycited by 18
2024Certified Robustness to Data Poisoning in Gradient-Based Trainingcited by 18
2021Robust Federated Learning with Attack-Adaptive Aggregationcited by 17
2021A Decentralized Federated Learning Framework via Committee Mechanism with Convergence Guaranteecited by 16
2023FedGT: Identification of Malicious Clients in Federated Learning with Secure Aggregationcited by 16
2021FedCCEA : A Practical Approach of Client Contribution Evaluation for Federated Learningcited by 14
2023Defenses in Adversarial Machine Learning: A Surveycited by 14
2021Auto-weighted Robust Federated Learning with Corrupted Data Sourcescited by 12
2022Multi-Task Distributed Learning using Vision Transformer with Random Patch Permutationcited by 10
2023FLrce: Resource-Efficient Federated Learning with Early-Stopping Strategycited by 10
2021Byzantine-robust Federated Learning through Spatial-temporal Analysis of Local Model Updatescited by 8
2021Federated Learning for Privacy-Preserving Open Innovation Future on Digital Healthcited by 8
2022Long-Short History of Gradients is All You Need: Detecting Malicious and Unreliable Clients in Federated Learningcited by 7
2023When Federated Learning meets Watermarking: A Comprehensive Overview of Techniques for Intellectual Property Protectioncited by 7
2024Towards Efficient and Certified Recovery from Poisoning Attacks in Federated Learningcited by 7
2023Resisting Backdoor Attacks in Federated Learning via Bidirectional Elections and Individual Perspectivecited by 6
2025FedSV: Byzantine-Robust Federated Learning via Shapley Valuecited by 6
2022Hijack Vertical Federated Learning Models As One Partycited by 5
2024Fine-Tuning Personalization in Federated Learning to Mitigate Adversarial Clientscited by 5
2021Federated Learning: Issues in Medical Applicationcited by 4
2021Bristle: Decentralized Federated Learning in Byzantine, Non-i.i.d. Environmentscited by 4
2022Federated and Transfer Learning: A Survey on Adversaries and Defense Mechanismscited by 4
2023Backdoor Learning for NLP: Recent Advances, Challenges, and Future Research Directionscited by 4
2023Trustworthy Federated Learning: A Surveycited by 4
2024Communication-Efficient Byzantine-Resilient Federated Zero-Order Optimizationcited by 4
2026Exact Certification of Data-Poisoning Attacks Using Mixed-Integer Programmingcited by 4
2022Technical Report: Assisting Backdoor Federated Learning with Whole Population Knowledge Alignmentcited by 3
2023SPIRT: A Fault-Tolerant and Reliable Peer-to-Peer Serverless ML Training Architecturecited by 3
2024Fin-Fed-OD: Federated Outlier Detection on Financial Tabular Datacited by 3
2024BoBa: Boosting Backdoor Detection through Data Distribution Inference in Federated Learningcited by 3
2025FedEAT: A Robustness Optimization Framework for Federated LLMscited by 3
2025Don't Reach for the Stars: Rethinking Topology for Resilient Federated Learningcited by 3
2025Practical Framework for Privacy-Preserving and Byzantine-robust Federated Learningcited by 3
2021DID-eFed: Facilitating Federated Learning as a Service with Decentralized Identitiescited by 2
2021ABC-FL: Anomalous and Benign client Classification in Federated Learningcited by 2

50 most cited of 88 All 88 (JSON)