mlsanityData to 7 Oct 2026

FL-WBC: Enhancing Robustness against Model Poisoning Attacks in Federated Learning from a Client Perspective

arXiv 2110.13864 ↗First posted 26 Oct 2021cs.LG cs.AI cs.CVcited by 35

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) is a popular distributed learning framework that trains a global model through iterative communications between a central server and edge devices. Recent works have demonstrated that FL is vulnerable to model poisoning attacks. Several server-based defense approaches (e.g. robust aggregation), have been proposed to mitigate such attacks. However, we empirically show that under extremely strong attacks, these defensive methods fail to guarantee the robustness of FL. More importantly, we observe that as long as the global model is polluted, the impact of attacks on the global model will remain in subsequent rounds even if there are no subsequent attacks. In this work, we propose a client-based defense, named White Blood Cell for Federated Learning (FL-WBC), which can mitigate model poisoning attacks that have already polluted the global model. The key idea of FL-WBC is to identify the parameter space where long-lasting attack effect on parameters resides and perturb that space during local training. Furthermore, we derive a certified robustness guarantee against model poisoning attacks and a convergence guarantee to FedAvg after applying our FL-WBC. We conduct experiments on FasionMNIST and CIFAR10 to evaluate the defense against state-of-the-art model poisoning attacks. The results demonstrate that our method can effectively mitigate model poisoning attack impact on the global model within 5 communication rounds with nearly no accuracy drop under both IID and Non-IID settings. Our defense is also complementary to existing server-based robust aggregation approaches and can further improve the robustness of FL under extremely strong attacks.

Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). Builds on 20 of its 28 references that are in the map. First posted on arXiv 26 Oct 2021.

Builds on

20 of 28 references.

References · 20

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  3. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,220
  4. 2018How To Backdoor Federated Learningcited by 745
  5. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 698
  6. 2020On Adaptive Attacks to Adversarial Example Defensescited by 547
  7. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 479
  8. 2019On Evaluating Adversarial Robustnesscited by 442
  9. 2018Analyzing Federated Learning through an Adversarial Lenscited by 346
  10. 2018The Hidden Vulnerability of Distributed Learning in Byzantiumcited by 324
  11. 2019Robust Aggregation for Federated Learningcited by 314
  12. 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 307
8 more
  1. 2020FedML: A Research Library and Benchmark for Federated Machine Learningcited by 298
  2. 2019A Little Is Enough: Circumventing Defenses For Distributed Learningcited by 285
  3. 2019Can You Really Backdoor Federated Learning?cited by 250
  4. 2018Mitigating Sybils in Federated Learning Poisoningcited by 158
  5. 2019Byzantine-Robust Federated Machine Learning through Adaptive Model Averagingcited by 70
  6. 2020LotteryFL: Personalized and Communication-Efficient Federated Learning with Lottery Ticket Hypothesis on Non-IID Datasetscited by 60
  7. 2019Attack-Resistant Federated Learning with Residual-based Reweightingcited by 40
  8. 2018Universal Multi-Party Poisoning Attackscited by 17

Built on by

Cited by year (2026 to 7 Oct)

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

35 papers.

Sort:

By area:

  1. 2023Heterogeneous Federated Learning: State-of-the-art and Research Challengescited by 160
  2. 2022Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challengescited by 81
  3. 2022Client Selection in Federated Learning: Principles, Challenges, and Opportunitiescited by 62
  4. 2023Recent Advances on Federated Learning: A Systematic Surveycited by 40
  5. 2023Backdoor Attacks and Defenses in Federated Learning: Survey, Challenges and Future Research Directionscited by 33
  6. 2023FedSecurity: Benchmarking Attacks and Defenses in Federated Learning and Federated LLMscited by 19
  7. 2023Data and Model Poisoning Backdoor Attacks on Wireless Federated Learning, and the Defense Mechanisms: A Comprehensive Surveycited by 17
  8. 2024Threats and Defenses in Federated Learning Life Cycle: A Comprehensive Survey and Challengescited by 14
  9. 2023FedDefender: Client-Side Attack-Tolerant Federated Learningcited by 12
  10. 2024FRAG: Toward Federated Vector Database Management for Collaborative and Secure Retrieval-Augmented Generationcited by 12
  11. 2023G2uardFL: Safeguarding Federated Learning Against Backdoor Attacks through Attributed Client Graph Clusteringcited by 9
  12. 2022MixTailor: Mixed Gradient Aggregation for Robust Learning Against Tailored Attackscited by 5
23 more
  1. 2022Network-Level Adversaries in Federated Learningcited by 4
  2. 2023Trustworthy Federated Learning: A Surveycited by 4
  3. 2024Vertical Federated Unlearning via Backdoor Certificationcited by 4
  4. 2024Linkage on Security, Privacy and Fairness in Federated Learning: New Balances and New Perspectivescited by 3
  5. 2025Dual Defense: Enhancing Privacy and Mitigating Poisoning Attacks in Federated Learningcited by 3
  6. 2023Kick Bad Guys Out! Conditionally Activated Anomaly Detection in Federated Learning with Zero-Knowledge Proof Verificationcited by 2
  7. 2024Poisoning with A Pill: Circumventing Detection in Federated Learningcited by 2
  8. 2025On the Security and Privacy of Federated Learning: A Survey with Attacks, Defenses, Frameworks, Applications, and Future Directionscited by 2
  9. 2022Fabricated Flips: Poisoning Federated Learning without Datacited by 1
  10. 2025Secure Cluster-Based Hierarchical Federated Learning in Vehicular Networkscited by 1
  11. 2025BackFed: An Efficient & Standardized Benchmark Suite for Backdoor Attacks in Federated Learningcited by 1
  12. 2026Your Neighbors Know: Leveraging Local Neighborhoods for Backdoor Detection in Decentralized Learningcited by 1
  13. 2022FADE: Enabling Federated Adversarial Training on Heterogeneous Resource-Constrained Edge Devicescited by 0
  14. 2024Secure Hierarchical Federated Learning in Vehicular Networks Using Dynamic Client Selection and Anomaly Detectioncited by 0
  15. 2024SHFL: Secure Hierarchical Federated Learning Framework for Edge Networkscited by 0
  16. 2024Privacy Attack in Federated Learning is Not Easy: An Experimental Studycited by 0
  17. 2025Lossless Privacy-Preserving Aggregation for Decentralized Federated Learningcited by 0
  18. 2025Gradient Purification: Defense Against Poisoning Attack in Decentralized Federated Learningcited by 0
  19. 2025FedNIA: Noise-Induced Activation Analysis for Mitigating Data Poisoning in Federated Learningcited by 0
  20. 2025Robust Federated Learning against Model Perturbation in Edge Networkscited by 0
  21. 2025Hammer and Anvil: Toward a Theory of Backdoors in Federated Learningcited by 0
  22. 2026TriShield: Zero-Utility-Loss Defense Against Privacy Backdoors in Federated Language Model Fine-Tuning via Orthogonal Gradient Projection and Optimizer State Entanglementcited by 0
  23. 2026Upholding Robustness in Federated Learning: Trends, Emerging Strategies, and Research Opportunitiescited by 0