mlsanityData to 7 Oct 2026

Abnormal Client Behavior Detection in Federated Learning

arXiv 1910.09933 ↗First posted 22 Oct 2019cs.LG stat.MLcited by 39

Not on the map. Why?

Abstract (arXiv)

In federated learning systems, clients are autonomous in that their behaviors are not fully governed by the server. Consequently, a client may intentionally or unintentionally deviate from the prescribed course of federated model training, resulting in abnormal behaviors, such as turning into a malicious attacker or a malfunctioning client. Timely detecting those anomalous clients is therefore critical to minimize their adverse impacts. In this work, we propose to detect anomalous clients at the server side. In particular, we generate low-dimensional surrogates of model weight vectors and use them to perform anomaly detection. We evaluate our solution through experiments on image classification model training over the FEMNIST dataset. Experimental results show that the proposed detection-based approach significantly outperforms the conventional defense-based methods.

Key facts. Cited by 39 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 8; 2023: 3; 2024: 11; 2025: 6; 2026: 2.

39 papers.

Sort:

By area:

  1. 2022DeepSight: Mitigating Backdoor Attacks in Federated Learning Through Deep Model Inspectioncited by 78
  2. 2021From Distributed Machine Learning to Federated Learning: A Surveycited by 65
  3. 2021FedGEMS: Federated Learning of Larger Server Models via Selective Knowledge Fusioncited by 49
  4. 2021Challenges and Approaches for Mitigating Byzantine Attacks in Federated Learningcited by 46
  5. 2023BayBFed: Bayesian Backdoor Defense for Federated Learningcited by 23
  6. 2022A Survey of Graph-based Deep Learning for Anomaly Detection in Distributed Systemscited by 20
  7. 2022Scalable and Low-Latency Federated Learning with Cooperative Mobile Edge Networkingcited by 18
  8. 2022Combined Federated and Split Learning in Edge Computing for Ubiquitous Intelligence in Internet of Things: State of the Art and Future Directionscited by 14
  9. 2025Federated Continual Learning: Concepts, Challenges, and Solutionscited by 13
  10. 2021Towards Efficient Synchronous Federated Training: A Survey on System Optimization Strategiescited by 9
  11. 2021Federated Learning for Privacy-Preserving Open Innovation Future on Digital Healthcited by 8
  12. 2022Byzantines can also Learn from History: Fall of Centered Clipping in Federated Learningcited by 8
27 more
  1. 2024ACE: A Model Poisoning Attack on Contribution Evaluation Methods in Federated Learningcited by 5
  2. 2022Federated and Transfer Learning: A Survey on Adversaries and Defense Mechanismscited by 4
  3. 2022Using Anomaly Detection to Detect Poisoning Attacks in Federated Learning Applicationscited by 4
  4. 2021Towards On-Device Federated Learning: A Direct Acyclic Graph-based Blockchain Approachcited by 3
  5. 2024Fin-Fed-OD: Federated Outlier Detection on Financial Tabular Datacited by 3
  6. 2024Federated Behavioural Planes: Explaining the Evolution of Client Behaviour in Federated Learningcited by 3
  7. 2024Tackling Selfish Clients in Federated Learningcited by 3
  8. 2024FedAD-Bench: A Unified Benchmark for Federated Unsupervised Anomaly Detection in Tabular Datacited by 3
  9. 2021DistFL: Distribution-aware Federated Learning for Mobile Scenarioscited by 2
  10. 2024Heterogeneity-Aware Cooperative Federated Edge Learning with Adaptive Computation and Communication Compressioncited by 2
  11. 2025Practical Framework for Privacy-Preserving and Byzantine-robust Federated Learningcited by 2
  12. 2021Stochastic Alternating Direction Method of Multipliers for Byzantine-Robust Distributed Learningcited by 1
  13. 2021Byzantine-Robust Federated Learning via Credibility Assessment on Non-IID Datacited by 1
  14. 2023Welfare and Fairness Dynamics in Federated Learning: A Client Selection Perspectivecited by 1
  15. 2024GANcrop: A Contrastive Defense Against Backdoor Attacks in Federated Learningcited by 1
  16. 2024Understanding Byzantine Robustness in Federated Learning with A Black-box Servercited by 1
  17. 2024CoopASD: Cooperative Machine Anomalous Sound Detection with Privacy Concernscited by 1
  18. 2024Byzantine-Robust Federated Learning: An Overview With Focus on Developing Sybil-based Attacks to Backdoor Augmented Secure Aggregation Protocolscited by 1
  19. 2025FedUP: Efficient Pruning-based Federated Unlearning for Model Poisoning Attackscited by 1
  20. 2022Federated Learning -- Methods, Applications and beyondcited by 0
  21. 2023The Landscape of Modern Machine Learning: A Review of Machine, Distributed and Federated Learningcited by 0
  22. 2024Fed-Credit: Robust Federated Learning with Credibility Managementcited by 0
  23. 2025Decoding FL Defenses: Systemization, Pitfalls, and Remediescited by 0
  24. 2025FedNIA: Noise-Induced Activation Analysis for Mitigating Data Poisoning in Federated Learningcited by 0
  25. 2025Adaptive Decentralized Federated Learning for Robust Optimizationcited by 0
  26. 2026Sample Selection Using Multi-Task Autoencoders in Federated Learning with Non-IID Datacited by 0
  27. 2026Federated Attention Autoencoders with a Stochastic Aggregation Scheme for Anomaly Detectioncited by 0