mlsanityData to 7 Oct 2026

Identify Backdoored Model in Federated Learning via Individual Unlearning

arXiv 2411.01040 ↗First posted 1 Nov 2024cs.LG cs.CR cs.DCcited by 4

Not on the map. Why?

Abstract (arXiv)

Backdoor attacks present a significant threat to the robustness of Federated Learning (FL) due to their stealth and effectiveness. They maintain both the main task of the FL system and the backdoor task simultaneously, causing malicious models to appear statistically similar to benign ones, which enables them to evade detection by existing defense methods. We find that malicious parameters in backdoored models are inactive on the main task, resulting in a significantly large empirical loss during the machine unlearning process on clean inputs. Inspired by this, we propose MASA, a method that utilizes individual unlearning on local models to identify malicious models in FL. To improve the performance of MASA in challenging non-independent and identically distributed (non-IID) settings, we design pre-unlearning model fusion that integrates local models with knowledge learned from other datasets to mitigate the divergence in their unlearning behaviors caused by the non-IID data distributions of clients. Additionally, we propose a new anomaly detection metric with minimal hyperparameters to filter out malicious models efficiently. Extensive experiments on IID and non-IID datasets across six different attacks validate the effectiveness of MASA. To the best of our knowledge, this is the first work to leverage machine unlearning to identify malicious models in FL. Code is available at urlhttps://github.com/JiiahaoXU/MASA.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 32 of its 53 references that are in the map. First posted on arXiv 1 Nov 2024.

Builds on

32 of 53 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  5. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,052
  6. 2019Machine Unlearningcited by 1,020
  7. 2018How To Backdoor Federated Learningcited by 745
  8. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 698
  9. 2022StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasetscited by 489
  10. 2020FLTrust: Byzantine-robust Federated Learning via Trust Bootstrappingcited by 330
  11. 2018The Hidden Vulnerability of Distributed Learning in Byzantiumcited by 324
  12. 2019Robust Aggregation for Federated Learningcited by 314
20 more
  1. 2021Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networkscited by 313
  2. 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 307
  3. 2019A Little Is Enough: Circumventing Defenses For Distributed Learningcited by 285
  4. 2021Adversarial Neuron Pruning Purifies Backdoored Deep Modelscited by 230
  5. 2021Federated Learning for Open Bankingcited by 138
  6. 2022Neurotoxin: Durable Backdoors in Federated Learningcited by 97
  7. 2021CRFL: Certifiably Robust Federated Learning against Backdoor Attackscited by 91
  8. 2020Defending against Backdoors in Federated Learning with Robust Learning Ratecited by 82
  9. 2022DeepSight: Mitigating Backdoor Attacks in Federated Learning Through Deep Model Inspectioncited by 78
  10. 2020Differentially Private Secure Multi-Party Computation for Federated Learning in Financial Applicationscited by 58
  11. 2023Reconstructive Neuron Pruning for Backdoor Defensecited by 56
  12. 2021Approximate Byzantine Fault-Tolerance in Distributed Optimizationcited by 27
  13. 2023On the Vulnerability of Backdoor Defenses for Federated Learningcited by 27
  14. 2020Federated Learning in the Sky: Aerial-Ground Air Quality Sensing Framework with UAV Swarmscited by 26
  15. 2023Multi-metrics adaptively identifies backdoors in Federated learningcited by 23
  16. 2021Adversarial training in communication constrained federated learningcited by 17
  17. 2024BackdoorIndicator: Leveraging OOD Data for Proactive Backdoor Detection in Federated Learningcited by 17
  18. 2024Achieving Byzantine-Resilient Federated Learning via Layer-Adaptive Sparsified Model Aggregationcited by 13
  19. 2023Get Rid Of Your Trail: Remotely Erasing Backdoors in Federated Learningcited by 12
  20. 2022PerDoor: Persistent Non-Uniform Backdoors in Federated Learning using Adversarial Perturbationscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 1.

4 papers.

  1. 2025Detecting Backdoor Attacks in Federated Learning via Direction Alignment Inspectioncited by 13
  2. 2025On the Out-of-Distribution Backdoor Attack for Federated Learningcited by 1
  3. 2025Hammer and Anvil: Toward a Theory of Backdoors in Federated Learningcited by 0
  4. 2026Defending Against Backdoor Attacks via Alignment Checking in Model-Contrastive Federated Learningcited by 0