mlsanityData to 14 Oct 2026

FL-CLEANER: byzantine and backdoor defense by CLustering Errors of Activation maps in Non-iid fedErated leaRning

arXiv 2501.12123 ↗First posted 21 Jan 2025cs.CR cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) enables clients to collaboratively train a global model using their local datasets while reinforcing data privacy, but it is prone to poisoning attacks. Existing defense mechanisms assume that clients' data are independent and identically distributed (IID), making them ineffective in real-world applications where data are non-IID. This paper presents FL-CLEANER, the first defense capable of filtering both byzantine and backdoor attackers' model updates in a non-IID FL environment. The originality of FL-CLEANER is twofold. First, it relies on a client confidence score derived from the reconstruction errors of each client's model activation maps for a given trigger set, with reconstruction errors obtained by means of a Conditional Variational Autoencoder trained according to a novel server-side strategy. Second, it uses an original ad-hoc trust propagation algorithm we propose. Based on previous client scores, it allows building a cluster of benign clients while flagging potential attackers. Experimental results on the datasets MNIST and FashionMNIST demonstrate the efficiency of FL-CLEANER against Byzantine attackers as well as to some state-of-the-art backdoors in non-IID scenarios; it achieves a close-to-zero (<1%) benign client misclassification rate, even in the absence of an attack, and achieves strong performance compared to state of the art defenses.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 36 of its 58 references that are in the map. First posted on arXiv 21 Jan 2025.

Builds on

36 of 58 references.

References · 36

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  4. 2019Advances and Open Problems in Federated Learningcited by 3,046
  5. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  6. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  7. 2018Federated Learning with Non-IID Datacited by 1,108
  8. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 851
  9. 2018How To Backdoor Federated Learningcited by 765
  10. 2015Generating Sentences from a Continuous Spacecited by 612
  11. 2018Federated Learning for Mobile Keyboard Predictioncited by 572
  12. 2021Federated Learning Based on Dynamic Regularizationcited by 562
24 more
  1. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 493
  2. 2016Tutorial on Variational Autoencoderscited by 409
  3. 2019Bayesian Nonparametric Federated Learning of Neural Networkscited by 387
  4. 2018The Hidden Vulnerability of Distributed Learning in Byzantiumcited by 329
  5. 2022FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correctioncited by 181
  6. 2018Mitigating Sybils in Federated Learning Poisoningcited by 161
  7. 2022FLDetector: Defending Federated Learning Against Model Poisoning Attacks via Detecting Malicious Clientscited by 125
  8. 2015Attribute2Image: Conditional Image Generation from Visual Attributescited by 93
  9. 2020Learning to Detect Malicious Clients for Robust Federated Learningcited by 88
  10. 2022DeepSight: Mitigating Backdoor Attacks in Federated Learning Through Deep Model Inspectioncited by 81
  11. 2023Federated Learning for Medical Image Analysis: A Surveycited by 78
  12. 2020Anomaly Detection With Conditional Variational Autoencoderscited by 46
  13. 2020Mitigating Backdoor Attacks in Federated Learningcited by 39
  14. 2021Emerging Trends in Federated Learning: From Model Fusion to Federated X Learningcited by 35
  15. 2023Backdoor Attacks and Defenses in Federated Learning: Survey, Challenges and Future Research Directionscited by 33
  16. 2023Robust Distributed Learning: Tight Error Bounds and Breakdown Point under Data Heterogeneitycited by 26
  17. 2017Byzantine-Tolerant Machine Learningcited by 19
  18. 2024Distributed Backdoor Attacks on Federated Graph Learning and Certified Defensescited by 15
  19. 2015A Probabilistic Theory of Deep Learningcited by 11
  20. 2023Beyond Vanilla Variational Autoencoders: Detecting Posterior Collapse in Conditional and Hierarchical Variational Autoencoderscited by 7
  21. 2023When Federated Learning meets Watermarking: A Comprehensive Overview of Techniques for Intellectual Property Protectioncited by 7
  22. 2023FLEDGE: Ledger-based Federated Learning Resilient to Inference and Backdoor Attackscited by 4
  23. 2022Technical Report: Assisting Backdoor Federated Learning with Whole Population Knowledge Alignmentcited by 3
  24. 2022DICTION:DynamIC robusT whIte bOx watermarkiNg scheme for deep neural networkscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023Mitigating Backdoors in Federated Learning with FLD
  2. 2025Buffer is All You Need: Defending Federated Learning against Backdoor Attacks under Non-iids via Buffering
  3. 2023FedGrad: Mitigating Backdoor Attacks in Federated Learning Through Local Ultimate Gradients Inspection
  4. 2022FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning
  5. 2024Client-Side Patching against Backdoor Attacks in Federated Learning
  6. 2023FLShield: A Validation Based Federated Learning Framework to Defend Against Poisoning Attacks
  7. 2023On the Vulnerability of Backdoor Defenses for Federated Learning
  8. 2024Securing Federated Learning against Backdoor Threats with Foundation Model Integration