mlsanityData to 13 Oct 2026

Challenges and Approaches for Mitigating Byzantine Attacks in Federated Learning

arXiv 2112.14468 ↗First posted 29 Dec 2021cs.CR cs.AI cs.DCcited by 47

Not on the map. Why?

Abstract (arXiv)

Recently emerged federated learning (FL) is an attractive distributed learning framework in which numerous wireless end-user devices can train a global model with the data remained autochthonous. Compared with the traditional machine learning framework that collects user data for centralized storage, which brings huge communication burden and concerns about data privacy, this approach can not only save the network bandwidth but also protect the data privacy. Despite the promising prospect, byzantine attack, an intractable threat in conventional distributed network, is discovered to be rather efficacious against FL as well. In this paper, we conduct a comprehensive investigation of the state-of-the-art strategies for defending against byzantine attacks in FL. We first provide a taxonomy for the existing defense solutions according to the techniques they used, followed by an across-the-board comparison and discussion. Then we propose a new byzantine attack method called weight attack to defeat those defense schemes, and conduct experiments to demonstrate its threat. The results show that existing defense solutions, although abundant, are still far from fully protecting FL. Finally, we indicate possible countermeasures for weight attack, and highlight several challenges and future research directions for mitigating byzantine attacks in FL.

Key facts. Cited by 47 papers in the map (data through 13 Oct 2026). Builds on 14 of its 31 references that are in the map. First posted on arXiv 29 Dec 2021.

Builds on

14 of 31 references.

References · 14

  1. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  2. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,470
  3. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 711
  4. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 708
  5. 2020FLTrust: Byzantine-robust Federated Learning via Trust Bootstrappingcited by 339
  6. 2018The Hidden Vulnerability of Distributed Learning in Byzantiumcited by 326
  7. 2019Robust Aggregation for Federated Learningcited by 316
  8. 2018Mitigating Sybils in Federated Learning Poisoningcited by 160
  9. 2018RSA: Byzantine-Robust Stochastic Aggregation Methods for Distributed Learning from Heterogeneous Datasetscited by 148
  10. 2020Federated Semi-Supervised Learning with Inter-Client Consistency & Disjoint Learningcited by 112
  11. 2018Generalized Byzantine-tolerant SGDcited by 94
  12. 2019Byzantine-Robust Federated Machine Learning through Adaptive Model Averagingcited by 70
2 more
  1. 2019Abnormal Client Behavior Detection in Federated Learningcited by 40
  2. 2021FedTriNet: A Pseudo Labeling Method with Three Players for Federated Semi-supervised Learningcited by 7

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2022: 4; 2023: 10; 2024: 13; 2025: 15; 2026: 5.

47 papers.

Sort:

By area:

  1. 2022Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challengescited by 84
  2. 2023An Experimental Study of Byzantine-Robust Aggregation Schemes in Federated Learningcited by 32
  3. 2023Over-The-Air Federated Learning: Status Quo, Open Challenges, and Future Directionscited by 21
  4. 2024RFLPA: A Robust Federated Learning Framework against Poisoning Attacks with Secure Aggregationcited by 10
  5. 2023A Survey on Vulnerability of Federated Learning: A Learning Algorithm Perspectivecited by 9
  6. 2023When Federated Learning meets Watermarking: A Comprehensive Overview of Techniques for Intellectual Property Protectioncited by 7
  7. 2024Byzantine-Robust Aggregation for Securing Decentralized Federated Learningcited by 7
  8. 2025MARS: A Malignity-Aware Backdoor Defense in Federated Learningcited by 7
  9. 2023AGRAMPLIFIER: Defending Federated Learning Against Poisoning Attacks Through Local Update Amplificationcited by 5
  10. 2024ACE: A Model Poisoning Attack on Contribution Evaluation Methods in Federated Learningcited by 5
  11. 2022Federated learning with incremental clustering for heterogeneous datacited by 4
  12. 2022Using Anomaly Detection to Detect Poisoning Attacks in Federated Learning Applicationscited by 4
35 more
  1. 2024Federated Behavioural Planes: Explaining the Evolution of Client Behaviour in Federated Learningcited by 4
  2. 2022Edge Security: Challenges and Issuescited by 3
  3. 2023Protecting Federated Learning from Extreme Model Poisoning Attacks via Multidimensional Time Series Anomaly Detectioncited by 3
  4. 2023MISA: Unveiling the Vulnerabilities in Split Federated Learningcited by 3
  5. 2024FedRDF: A Robust and Dynamic Aggregation Function against Poisoning Attacks in Federated Learningcited by 3
  6. 2023A Framework for Incentivized Collaborative Learningcited by 2
  7. 2023FedBayes: A Zero-Trust Federated Learning Aggregation to Defend Against Adversarial Attackscited by 2
  8. 2025Improving (α, f)-Byzantine Resilience in Federated Learning via layerwise aggregation and cosine distancecited by 2
  9. 2023Can We Trust the Similarity Measurement in Federated Learning?cited by 1
  10. 2024Mitigating Malicious Attacks in Federated Learning via Confidence-aware Defensecited by 1
  11. 2024Federated Learning Nodes Can Reconstruct Peers' Image Datacited by 1
  12. 2024Byzantine-Robust Federated Learning: An Overview With Focus on Developing Sybil-based Attacks to Backdoor Augmented Secure Aggregation Protocolscited by 1
  13. 2025Byzantine-Resilient Over-the-Air Federated Learning under Zero-Trust Architecturecited by 1
  14. 2025Approximate Agreement Algorithms for Byzantine Collaborative Learningcited by 1
  15. 2025Zero-Trust Foundation Models: A New Paradigm for Secure and Collaborative Artificial Intelligence for Internet of Thingscited by 1
  16. 2025On the Fragility of Contribution Score Computation in Federated Learningcited by 1
  17. 2024Fed-Credit: Robust Federated Learning with Credibility Managementcited by 0
  18. 2024Data Quality in Edge Machine Learning: A State-of-the-Art Surveycited by 0
  19. 2024Impact of Network Topology on Byzantine Resilience in Decentralized Federated Learningcited by 0
  20. 2024RAB2-DEF: Dynamic and explainable defense against adversarial attacks in Federated Learning to fair poor clientscited by 0
  21. 2024DistDD: Distributed Data Distillation Aggregation through Gradient Matchingcited by 0
  22. 2025CO-DEFEND: Continuous Decentralized Federated Learning for Secure DoH-Based Threat Detectioncited by 0
  23. 2025ATR-Bench: A Federated Learning Benchmark for Adaptation, Trust, and Reasoningcited by 0
  24. 2025Coded Robust Aggregation for Distributed Learning under Byzantine Attackscited by 0
  25. 2025Realistic Urban Traffic Generator using Decentralized Federated Learning for the SUMO simulatorcited by 0
  26. 2025Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updatescited by 0
  27. 2025Centroid Approximation for Byzantine-Tolerant Federated Learningcited by 0
  28. 2025Online Decentralized Federated Multi-task Learning With Trustworthiness in Cyber-Physical Systemscited by 0
  29. 2025ProDiGy: Proximity- and Dissimilarity-Based Byzantine-Robust Federated Learningcited by 0
  30. 2025Adaptive Decentralized Federated Learning for Robust Optimizationcited by 0
  31. 2026Resilient Federated Chain: Transforming Blockchain Consensus into an Active Defense Layer for Federated Learningcited by 0
  32. 2026Decentralized Orchestration Architecture for Fluid Computing: A Secure Distributed AI Use Casecited by 0
  33. 2026Byzantine-Robust Optimization under (L0, L1)-Smoothnesscited by 0
  34. 2026FedDetox: Robust Federated SLM Alignment via On-Device Data Sanitizationcited by 0
  35. 2026FedEDAuth -- Federated Embedding Distribution Authentication for Counterfeit IC Detectioncited by 0