mlsanityData to 7 Oct 2026

Federated unlearning and poisoning

213 papers0 this weekHigh confidence in this grouping: the papers form one clear topicHigh confidence in this grouping: the papers form one clear topic · About

Keywords: federated, federated learning, unlearning, clients, federated unlearning

Key facts. Federated unlearning and poisoning: 213 papers on arXiv since 2021 (data through 7 Oct 2026). 52 of its 213 mapped papers (24%) cite “The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining” (2022, arXiv 2203.07320). 45 of its 213 mapped papers (21%) cite “Federated Unlearning: How to Efficiently Erase a Client in FL?” (2022, arXiv 2207.05521).

What’s new

Nothing new since 24 Sep. Latest: 3 Sep 2026.

Foundations

Most cited by papers here

  1. The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining2022cited by 52 here
  2. Federated Unlearning: How to Efficiently Erase a Client in FL?2022cited by 45 here
  3. Federated Unlearning via Class-Discriminative Pruning2021cited by 43 here
  4. Federated Unlearning with Knowledge Distillation2022cited by 36 here
  5. A Survey on Federated Unlearning: Challenges, Methods, and Future Directions2023cited by 35 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2021Remember What You Want to Forget: Algorithms for Machine Unlearningcited by 16 here
  2. 2021On the Necessity of Auditable Algorithmic Definitions for Machine Unlearningcited by 10 here
  3. 2022The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retrainingcited by 52 here
  4. 2022Federated Unlearning: How to Efficiently Erase a Client in FL?cited by 45 here
  5. 2022A Survey of Machine Unlearningcited by 19 here
  6. 2023A Survey on Federated Unlearning: Challenges, Methods, and Future Directionscited by 35 here
  7. 2024Federated Unlearning: A Survey on Methods, Design Guidelines, and Evaluation Metricscited by 17 here
  8. 2025NoT: Federated Unlearning via Weight Negationcited by 9 here
16 more it builds on, not in this chain
  1. 2021Membership Inference Attacks on Machine Learning: A Surveycited by 11 here
  2. 2021Graph Unlearningcited by 8 here
  3. 2021Adaptive Machine Unlearningcited by 8 here
  4. 2021Federated Unlearning via Class-Discriminative Pruningcited by 43 here
  5. 2021Fast Yet Effective Machine Unlearningcited by 12 here
  6. 2021Membership Inference Attacks From First Principlescited by 15 here
  7. 2022Federated Unlearning with Knowledge Distillationcited by 36 here
  8. 2022Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks using an Incompetent Teachercited by 15 here
  9. 2022VeriFi: Towards Verifiable Federated Unlearningcited by 28 here
  10. 2022SIFU: Sequential Informed Federated Unlearning for Efficient and Provable Client Unlearning in Federated Optimizationcited by 9 here
  11. 2023Heterogeneous Federated Knowledge Graph Embedding Learning and Unlearningcited by 14 here
  12. 2023Towards Unbounded Machine Unlearningcited by 9 here
  13. 2023Subspace based Federated Unlearningcited by 10 here
  14. 2024Communication Efficient and Provable Federated Unlearningcited by 11 here
  15. 2024Unlearning during Learning: An Efficient Federated Machine Unlearning Methodcited by 12 here
  16. 2024Federated Unlearning with Gradient Descent and Conflict Mitigationcited by 13 here

The 24 most cited of 317.

Browse

30 of 213, ranked 6–35

  1. 6VeriFi: Towards Verifiable Federated Unlearning202228
  2. 7Federated Unlearning: A Survey on Methods, Design Guidelines, and Evaluation Metrics202417
  3. 8Heterogeneous Federated Knowledge Graph Embedding Learning and Unlearning202314
  4. 9Federated Unlearning with Gradient Descent and Conflict Mitigation202413
  5. 10Unlearning during Learning: An Efficient Federated Machine Unlearning Method202412
  6. 11Communication Efficient and Provable Federated Unlearning202411
  7. 12Subspace based Federated Unlearning202310
  8. 13NoT: Federated Unlearning via Weight Negation20259
  9. 14SIFU: Sequential Informed Federated Unlearning for Efficient and Provable Client Unlearning in Federated Optimization20229
  10. 15Unlearning through Knowledge Overwriting: Reversible Federated Unlearning via Selective Sparse Adapter20258
All 30
  1. 16Ferrari: Federated Feature Unlearning via Optimizing Feature Sensitivity20247
  2. 17FRAMU: Attention-based Machine Unlearning using Federated Reinforcement Learning20237
  3. 18QuickDrop: Efficient Federated Unlearning by Integrated Dataset Distillation20236
  4. 19Subject Membership Inference Attacks in Federated Learning20226
  5. 20Machine Unlearning of Federated Clusters20226
  6. 21Forget-SVGD: Particle-Based Bayesian Federated Unlearning20216
  7. 22Enable the Right to be Forgotten with Federated Client Unlearning in Medical Imaging20245
  8. 23Class-wise Federated Unlearning: Harnessing Active Forgetting with Teacher-Student Memory Generation20235
  9. 24Bayesian Variational Federated Learning and Unlearning in Decentralized Networks20215
  10. 25Scalable Federated Unlearning via Isolated and Coded Sharding20244
  11. 26Federated Unlearning: a Perspective of Stability and Fairness20244
  12. 27Membership Inference Attacks and Defenses in Federated Learning: A Survey20244
  13. 28FedCIP: Federated Client Intellectual Property Protection with Traitor Tracking20234
  14. 29SecureCut: Federated Gradient Boosting Decision Trees with Efficient Machine Unlearning20234
  15. 30Compressed Particle-Based Federated Bayesian Learning and Unlearning20224
  16. 31FedTracker: Furnishing Ownership Verification and Traceability for Federated Learning Model20224
  17. 32Efficient passive membership inference attack in federated learning20214
  18. 33Blockchain-enabled Trustworthy Federated Unlearning20243
  19. 34FedMIA: An Effective Membership Inference Attack Exploiting "All for One" Principle in Federated Learning20243
  20. 35Goldfish: An Efficient Federated Unlearning Framework20243