mlsanityData to 14 Oct 2026

BaFFLe: Backdoor detection via Feedback-based Federated Learning

arXiv 2011.02167 ↗First posted 4 Nov 2020cs.CR cs.LGcited by 53

Not on the map. Why?

Abstract (arXiv)

Recent studies have shown that federated learning (FL) is vulnerable to poisoning attacks that inject a backdoor into the global model. These attacks are effective even when performed by a single client, and undetectable by most existing defensive techniques. In this paper, we propose Backdoor detection via Feedback-based Federated Learning (BAFFLE), a novel defense to secure FL against backdoor attacks. The core idea behind BAFFLE is to leverage data of multiple clients not only for training but also for uncovering model poisoning. We exploit the availability of diverse datasets at the various clients by incorporating a feedback loop into the FL process, to integrate the views of those clients when deciding whether a given model update is genuine or not. We show that this powerful construct can achieve very high detection rates against state-of-the-art backdoor attacks, even when relying on straightforward methods to validate the model. Through empirical evaluation using the CIFAR-10 and FEMNIST datasets, we show that by combining the feedback loop with a method that suspects poisoning attempts by assessing the per-class classification performance of the updated model, BAFFLE reliably detects state-of-the-art backdoor attacks with a detection accuracy of 100% and a false-positive rate below 5%. Moreover, we show that our solution can detect adaptive attacks aimed at bypassing the defense.

Key facts. Cited by 53 papers in the map (data through 14 Oct 2026). First posted on arXiv 4 Nov 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 3; 2022: 7; 2023: 26; 2024: 5; 2025: 7; 2026: 5.

53 papers.

Sort:

By area:

  1. 2023Heterogeneous Federated Learning: State-of-the-art and Research Challengescited by 161
  2. 2021CRFL: Certifiably Robust Federated Learning against Backdoor Attackscited by 91
  3. 2022Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challengescited by 84
  4. 2022DeepSight: Mitigating Backdoor Attacks in Federated Learning Through Deep Model Inspectioncited by 81
  5. 2022FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learningcited by 37
  6. 2023Backdoor Attacks and Defenses in Federated Learning: Survey, Challenges and Future Research Directionscited by 33
  7. 2023An Experimental Study of Byzantine-Robust Aggregation Schemes in Federated Learningcited by 32
  8. 2023Integration of Large Language Models and Federated Learningcited by 31
  9. 2022CrowdGuard: Federated Backdoor Detection in Federated Learningcited by 27
  10. 2023On the Vulnerability of Backdoor Defenses for Federated Learningcited by 27
  11. 2023FreqFed: A Frequency Analysis-Based Approach for Mitigating Poisoning Attacks in Federated Learningcited by 27
  12. 2023A Survey of Trustworthy Federated Learning with Perspectives on Security, Robustness, and Privacycited by 24
38 more
  1. 2023BayBFed: Bayesian Backdoor Defense for Federated Learningcited by 23
  2. 2023Multi-metrics adaptively identifies backdoors in Federated learningcited by 23
  3. 2023Federated Learning for Computer Visioncited by 22
  4. 2023Chameleon: Adapting to Peer Images for Planting Durable Backdoors in Federated Learningcited by 21
  5. 2023AI-native Interconnect Framework for Integration of Large Language Model Technologies in 6G Systemscited by 19
  6. 2023Data and Model Poisoning Backdoor Attacks on Wireless Federated Learning, and the Defense Mechanisms: A Comprehensive Surveycited by 18
  7. 2023FLShield: A Validation Based Federated Learning Framework to Defend Against Poisoning Attackscited by 15
  8. 2023Get Rid Of Your Trail: Remotely Erasing Backdoors in Federated Learningcited by 13
  9. 2022Collaboration in Participant-Centric Federated Learning: A Game-Theoretical Perspectivecited by 9
  10. 2023A Survey on Vulnerability of Federated Learning: A Learning Algorithm Perspectivecited by 9
  11. 2022ScionFL: Efficient and Robust Secure Quantized Aggregationcited by 8
  12. 2023FLTracer: Accurate Poisoning Attack Provenance in Federated Learningcited by 8
  13. 2023Differential Analysis of Triggers and Benign Features for Black-Box DNN Backdoor Detectioncited by 6
  14. 2022Hijack Vertical Federated Learning Models As One Partycited by 5
  15. 2023Trustworthy Federated Learning: A Surveycited by 4
  16. 2023FLEDGE: Ledger-based Federated Learning Resilient to Inference and Backdoor Attackscited by 4
  17. 2021PRECAD: Privacy-Preserving and Robust Federated Learning via Crypto-Aided Differential Privacycited by 3
  18. 2023Poisoning Attacks and Defenses in Federated Learning: A Surveycited by 3
  19. 2023FLAIRS: FPGA-Accelerated Inference-Resistant & Secure Federated Learningcited by 3
  20. 2024BoBa: Boosting Backdoor Detection through Data Distribution Inference in Federated Learningcited by 3
  21. 2025Practical Framework for Privacy-Preserving and Byzantine-robust Federated Learningcited by 3
  22. 2024EmInspector: Combating Backdoor Attacks in Federated Self-Supervised Learning Through Embedding Inspectioncited by 2
  23. 2025Robust Knowledge Distillation in Federated Learning: Counteracting Backdoor Attackscited by 2
  24. 2023Avoid Adversarial Adaption in Federated Learning by Multi-Metric Investigationscited by 1
  25. 2023TrustFed: A Reliable Federated Learning Framework with Malicious-Attack Resistancecited by 1
  26. 2024On the Conflict of Robustness and Learning in Collaborative Machine Learningcited by 1
  27. 2025FL-PLAS: Federated Learning with Partial Layer Aggregation for Backdoor Defense Against High-Ratio Malicious Clientscited by 1
  28. 2025Poison Once, Refuse Forever: Weaponizing Alignment for Injecting Bias in LLMscited by 1
  29. 2026Your Neighbors Know: Leveraging Local Neighborhoods for Backdoor Detection in Decentralized Learningcited by 1
  30. 2021Anomaly Localization in Model Gradients Under Backdoor Attacks Against Federated Learningcited by 0
  31. 2023Covert Communication Based on the Poisoning Attack in Federated Learningcited by 0
  32. 2023Adversarial Client Detection via Non-parametric Subspace Monitoring in the Internet of Federated Thingscited by 0
  33. 2024Data Distribution Shifts in (Industrial) Federated Learning as a Privacy Issuecited by 0
  34. 2024SHFL: Secure Hierarchical Federated Learning Framework for Edge Networkscited by 0
  35. 2025Decoding FL Defenses: Systemization, Pitfalls, and Remediescited by 0
  36. 2025FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrixcited by 0
  37. 2025Poison to Detect: Detection of Targeted Overfitting in Federated Learningcited by 0
  38. 2026TASER: Task-Aware Spectral Energy Refine for Backdoor Suppression in UAV Swarms Decentralized Federated Learningcited by 0

50 most cited of 53 All 53 (JSON)