mlsanityData to 14 Oct 2026

Federated Unlearning: How to Efficiently Erase a Client in FL?

arXiv 2207.05521 ↗First posted 12 Jul 2022cs.LG cs.CRcited by 95

On the map: LLM safety and security → Federated unlearning and poisoning

Abstract (arXiv)

With privacy legislation empowering the users with the right to be forgotten, it has become essential to make a model amenable for forgetting some of its training data. However, existing unlearning methods in the machine learning context can not be directly applied in the context of distributed settings like federated learning due to the differences in learning protocol and the presence of multiple actors. In this paper, we tackle the problem of federated unlearning for the case of erasing a client by removing the influence of their entire local data from the trained global model. To erase a client, we propose to first perform local unlearning at the client to be erased, and then use the locally unlearned model as the initialization to run very few rounds of federated learning between the server and the remaining clients to obtain the unlearned global model. We empirically evaluate our unlearning method by employing multiple performance measures on three datasets, and demonstrate that our unlearning method achieves comparable performance as the gold standard unlearning method of federated retraining from scratch, while being significantly efficient. Unlike prior works, our unlearning method neither requires global access to the data used for training nor the history of the parameter updates to be stored by the server or any of the clients.

Key facts. Cited by 95 papers in the map (data through 14 Oct 2026). Placed in Federated unlearning and poisoning, one of 12 directions in LLM safety and security. Builds on 28 of its 45 references that are in the map. First posted on arXiv 12 Jul 2022.

Builds on

28 of 45 references.

Closest ancestors · 3

Same direction, newest first

  1. 2022The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining14 Mar
  2. 2022Federated Unlearning with Knowledge Distillation24 Jan
  3. 2021Federated Unlearning via Class-Discriminative Pruning22 Oct

Other references · 25

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  3. 2019Advances and Open Problems in Federated Learningcited by 3,046
  4. 2020Extracting Training Data from Large Language Modelscited by 2,189
  5. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,106
  6. 2019Machine Unlearningcited by 1,061
  7. 2018How To Backdoor Federated Learningcited by 765
  8. 2022Quantifying Memorization Across Neural Language Modelscited by 763
  9. 2019Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networkscited by 618
  10. 2019Certified Data Removal from Machine Learning Modelscited by 535
  11. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 520
  12. 2019Making AI Forget You: Data Deletion in Machine Learningcited by 465
13 more
  1. 2021Remember What You Want to Forget: Algorithms for Machine Unlearningcited by 371
  2. 2020Amnesiac Machine Learningcited by 319
  3. 2020Descent-to-Delete: Gradient-Based Methods for Machine Unlearningcited by 311
  4. 2021Unrolling SGD: Understanding Factors Influencing Machine Unlearningcited by 279
  5. 2021Machine Unlearning of Features and Labelscited by 229
  6. 2018Adversarial Robustness Toolbox v1.0.0cited by 215
  7. 2020When Machine Unlearning Jeopardizes Privacycited by 198
  8. 2020Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observationscited by 180
  9. 2020Clean-Label Backdoor Attacks on Video Recognition Modelscited by 169
  10. 2020DeltaGrad: Rapid retraining of machine learning modelscited by 149
  11. 2020Machine Unlearning: Linear Filtration for Logit-based Classifierscited by 95
  12. 2021Does BERT Pretrained on Clinical Notes Reveal Sensitive Data?cited by 93
  13. 2022Backdoor Defense with Machine Unlearningcited by 65

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 3; 2023: 12; 2024: 37; 2025: 26; 2026: 17.

95 papers.

Sort:

By area:

  1. 2022A Survey of Machine Unlearningcited by 312
  2. 2024MUSE: Machine Unlearning Six-Way Evaluation for Language Modelscited by 261
  3. 2024Rethinking Machine Unlearning for Large Language Modelscited by 257
  4. 2024Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearningcited by 172
  5. 2023A Survey on Federated Unlearning: Challenges, Methods, and Future Directionscited by 63
  6. 2024Scissorhands: Scrub Data Influence via Connection Sensitivity in Networkscited by 52
  7. 2023Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomycited by 51
  8. 2024UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Modelscited by 50
  9. 2024Machine Unlearning for Image-to-Image Generative Modelscited by 47
  10. 2023Controlling the Extraction of Memorized Data from Large Language Models via Prompt-Tuningcited by 40
  11. 2024Threats, Attacks, and Defenses in Machine Unlearning: A Surveycited by 39
  12. 2023Backdoor Attacks and Defenses in Federated Learning: Survey, Challenges and Future Research Directionscited by 33
38 more
  1. 2024On Effects of Steering Latent Representation for Large Language Model Unlearningcited by 32
  2. 2024Federated Unlearning: A Survey on Methods, Design Guidelines, and Evaluation Metricscited by 27
  3. 2024WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Modelscited by 26
  4. 2024Score Forgetting Distillation: A Swift, Data-Free Method for Machine Unlearning in Diffusion Modelscited by 23
  5. 2024RKLD: Reverse KL-Divergence-based Knowledge Distillation for Unlearning Personal Information in Large Language Modelscited by 21
  6. 2025Learning to Unlearn while Retaining: Combating Gradient Conflicts in Machine Unlearningcited by 19
  7. 2022SIFU: Sequential Informed Federated Unlearning for Efficient and Provable Client Unlearning in Federated Optimizationcited by 18
  8. 2023Subspace based Federated Unlearningcited by 17
  9. 2024MUNBa: Machine Unlearning via Nash Bargainingcited by 17
  10. 2024Federated Unlearning with Gradient Descent and Conflict Mitigationcited by 17
  11. 2025Unlearning through Knowledge Overwriting: Reversible Federated Unlearning via Selective Sparse Adaptercited by 16
  12. 2024A Survey on Machine Unlearning: Techniques and New Emerged Privacy Riskscited by 15
  13. 2025NoT: Federated Unlearning via Weight Negationcited by 15
  14. 2024Unlearning during Learning: An Efficient Federated Machine Unlearning Methodcited by 14
  15. 2025Exact Unlearning of Finetuning Data via Model Merging at Scalecited by 14
  16. 2023Get Rid Of Your Trail: Remotely Erasing Backdoors in Federated Learningcited by 13
  17. 2024Federated Learning Priorities Under the European Union Artificial Intelligence Actcited by 13
  18. 2023QuickDrop: Efficient Federated Unlearning by Integrated Dataset Distillationcited by 11
  19. 2024Ferrari: Federated Feature Unlearning via Optimizing Feature Sensitivitycited by 11
  20. 2024Enable the Right to be Forgotten with Federated Client Unlearning in Medical Imagingcited by 9
  21. 2025Data Duplication: A Novel Multi-Purpose Attack Paradigm in Machine Unlearningcited by 9
  22. 2024Fast-FedUL: A Training-Free Federated Unlearning with Provable Skew Resiliencecited by 8
  23. 2024Towards Efficient and Certified Recovery from Poisoning Attacks in Federated Learningcited by 7
  24. 2024Federated Unlearning: a Perspective of Stability and Fairnesscited by 7
  25. 2024Multi-Objective Large Language Model Unlearningcited by 7
  26. 2026Attention Smoothing Is All You Need For Unlearningcited by 7
  27. 2024Vertical Federated Unlearning via Backdoor Certificationcited by 6
  28. 2023Forgettable Federated Linear Learning with Certified Data Unlearningcited by 5
  29. 2023Fast-NTK: Parameter-Efficient Unlearning for Large-Scale Modelscited by 5
  30. 2024Privacy-Preserving Federated Unlearning with Certified Client Removalcited by 5
  31. 2024Towards Privacy-Guaranteed Label Unlearning in Vertical Federated Learning: Few-Shot Forgetting without Disclosurecited by 5
  32. 2026EASE: Federated Multimodal Unlearning via Entanglement-Aware Anchor Closurecited by 5
  33. 2022Differentially Private Vertical Federated Learningcited by 4
  34. 2023On Knowledge Editing in Federated Learning: Perspectives, Challenges, and Future Directionscited by 4
  35. 2023Bkd-FedGNN: A Benchmark for Classification Backdoor Attacks on Federated Graph Neural Networkcited by 4
  36. 2023Defending Our Privacy With Backdoorscited by 4
  37. 2024How to Forget Clients in Federated Online Learning to Rank?cited by 4
  38. 2026Reinforcement Unlearning via Group Relative Policy Optimizationcited by 4

50 most cited of 95 All 95 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Towards Federated Domain Unlearning: Verification Methodologies and Challenges
  2. 2026Computation and Communication Efficient Federated Unlearning via On-server Gradient Conflict Mitigation and Expression
  3. 2023Exploring Federated Unlearning: Review, Comparison, and Insights
  4. 2024Communication Efficient and Provable Federated Unlearning
  5. 2024Update Selective Parameters: Federated Machine Unlearning Based on Model Explanation
  6. 2024Efficient Federated Unlearning with Adaptive Differential Privacy Preservation
  7. 2025FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks
  8. 2024Goldfish: An Efficient Federated Unlearning Framework