mlsanityData to 14 Oct 2026

FL-PLAS: Federated Learning with Partial Layer Aggregation for Backdoor Defense Against High-Ratio Malicious Clients

arXiv 2505.12019 ↗First posted 17 May 2025cs.CR cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) is gaining increasing attention as an emerging collaborative machine learning approach, particularly in the context of large-scale computing and data systems. However, the fundamental algorithm of FL, Federated Averaging (FedAvg), is susceptible to backdoor attacks. Although researchers have proposed numerous defense algorithms, two significant challenges remain. The attack is becoming more stealthy and harder to detect, and current defense methods are unable to handle 50% or more malicious users or assume an auxiliary server dataset. To address these challenges, we propose a novel defense algorithm, FL-PLAS, Federated Learning based on Partial Layer Aggregation Strategy. In particular, we divide the local model into a feature extractor and a classifier. In each iteration, the clients only upload the parameters of a feature extractor after local training. The server then aggregates these local parameters and returns the results to the clients. Each client retains its own classifier layer, ensuring that the backdoor labels do not impact other clients. We assess the effectiveness of FL-PLAS against state-of-the-art (SOTA) backdoor attacks on three image datasets and compare our approach to six defense strategies. The results of the experiment demonstrate that our methods can effectively protect local models from backdoor attacks. Without requiring any auxiliary dataset for the server, our method achieves a high main-task accuracy with a lower backdoor accuracy even under the condition of 90% malicious users with the attacks of trigger, semantic and edge-case.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 59 of its 74 references that are in the map. First posted on arXiv 17 May 2025.

Builds on

59 of 74 references.

References · 59

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  4. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  5. 2019Advances and Open Problems in Federated Learningcited by 3,046
  6. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,475
  7. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,106
  8. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,055
  9. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 851
  10. 2015The Limitations of Deep Learning in Adversarial Settingscited by 790
  11. 2018How To Backdoor Federated Learningcited by 765
  12. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 711
38 more
  1. 2020Personalized Federated Learning with Moreau Envelopescited by 618
  2. 2018Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networkscited by 580
  3. 2019Federated Learning with Personalization Layerscited by 541
  4. 2021Exploiting Shared Representations for Personalized Federated Learningcited by 541
  5. 2018Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networkscited by 519
  6. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 493
  7. 2018Spectral Signatures in Backdoor Attackscited by 484
  8. 2019STRIP: A Defence Against Trojan Attacks on Deep Neural Networkscited by 459
  9. 2018Detecting Backdoor Attacks on Deep Neural Networks by Activation Clusteringcited by 456
  10. 2020Backdoor Learning: A Surveycited by 426
  11. 2018Analyzing Federated Learning through an Adversarial Lenscited by 351
  12. 2020FLTrust: Byzantine-robust Federated Learning via Trust Bootstrappingcited by 346
  13. 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 309
  14. 2019A Little Is Enough: Circumventing Defenses For Distributed Learningcited by 288
  15. 2020Data Poisoning Attacks Against Federated Learning Systemscited by 275
  16. 2019Can You Really Backdoor Federated Learning?cited by 255
  17. 2018Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learningcited by 225
  18. 2017Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimizationcited by 197
  19. 2020Threats to Federated Learning: A Surveycited by 178
  20. 2017Neural Trojanscited by 153
  21. 2018RSA: Byzantine-Robust Stochastic Aggregation Methods for Distributed Learning from Heterogeneous Datasetscited by 149
  22. 2019Fall of Empires: Breaking Byzantine-tolerant SGD by Inner Product Manipulationcited by 141
  23. 2020Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustnesscited by 132
  24. 2019Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detectioncited by 124
  25. 2022Federated Learning with Partial Model Personalizationcited by 114
  26. 2018Is feature selection secure against training data poisoning?cited by 93
  27. 2020Learning to Detect Malicious Clients for Robust Federated Learningcited by 88
  28. 2016Data Poisoning Attacks on Factorization-Based Collaborative Filteringcited by 83
  29. 2020Defending against Backdoors in Federated Learning with Robust Learning Ratecited by 82
  30. 2018Technical Report: When Does Machine Learning FAIL? Generalized Transferability for Evasion and Poisoning Attackscited by 81
  31. 2018Backdooring Convolutional Neural Networks via Targeted Weight Perturbationscited by 69
  32. 2020End-to-End Evaluation of Federated Learning and Split Learning for Internet of Thingscited by 64
  33. 2019Terminal Brain Damage: Exposing the Graceless Degradation in Deep Neural Networks Under Hardware Fault Attackscited by 57
  34. 2018Poisoning Attacks to Graph-Based Recommender Systemscited by 56
  35. 2019Attacking Graph-based Classification via Manipulating the Graph Structurecited by 53
  36. 2020BaFFLe: Backdoor detection via Feedback-based Federated Learningcited by 53
  37. 2022FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learningcited by 37
  38. 2020One-pixel Signature: Characterizing CNN Models for Backdoor Detectioncited by 34

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026On the Tradeoffs of On-Device Generative Models in Federated Predictive Maintenance Systemscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2023Backdoor Attacks and Defenses in Federated Learning: Survey, Challenges and Future Research Directions
  2. 2023Mitigating Backdoors in Federated Learning with FLD
  3. 2021Meta Federated Learning
  4. 2022Backdoor Defense in Federated Learning Using Differential Testing and Outlier Detection
  5. 2023FedDefender: Backdoor Attack Defense in Federated Learning
  6. 2026FL-PBM: Pre-Training Backdoor Mitigation for Federated Learning
  7. 2023FedGrad: Mitigating Backdoor Attacks in Federated Learning Through Local Ultimate Gradients Inspection
  8. 2023BayBFed: Bayesian Backdoor Defense for Federated Learning