mlsanityData to 7 Oct 2026

A Survey on Federated Unlearning: Challenges, Methods, and Future Directions

arXiv 2310.20448 ↗First posted 31 Oct 2023cs.CRcited by 58

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

Abstract (arXiv)

In recent years, the notion of ``the right to be forgotten" (RTBF) has become a crucial aspect of data privacy for digital trust and AI safety, requiring the provision of mechanisms that support the removal of personal data of individuals upon their requests. Consequently, machine unlearning (MU) has gained considerable attention which allows an ML model to selectively eliminate identifiable information. Evolving from MU, federated unlearning (FU) has emerged to confront the challenge of data erasure within federated learning (FL) settings, which empowers the FL model to unlearn an FL client or identifiable information pertaining to the client. Nevertheless, the distinctive attributes of federated learning introduce specific challenges for FU techniques. These challenges necessitate a tailored design when developing FU algorithms. While various concepts and numerous federated unlearning schemes exist in this field, the unified workflow and tailored design of FU are not yet well understood. Therefore, this comprehensive survey delves into the techniques and methodologies in FU providing an overview of fundamental concepts and principles, evaluating existing federated unlearning algorithms, and reviewing optimizations tailored to federated learning. Additionally, it discusses practical applications and assesses their limitations. Finally, it outlines promising directions for future research.

Key facts. Cited by 58 papers in the map (data through 7 Oct 2026). Placed in Federated unlearning and poisoning, one of 12 directions in LLM safety and security. First posted on arXiv 31 Oct 2023.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 19; 2025: 26; 2026: 12.

58 papers.

Sort:

By area:

  1. 2024Rethinking Machine Unlearning for Large Language Modelscited by 247
  2. 2024Threats, Attacks, and Defenses in Machine Unlearning: A Surveycited by 34
  3. 2024Machine Unlearning: A Comprehensive Surveycited by 33
  4. 2024Federated Unlearning: A Survey on Methods, Design Guidelines, and Evaluation Metricscited by 25
  5. 2025BLUR: A Bi-Level Optimization Approach for LLM Unlearningcited by 23
  6. 2025Ten Challenging Problems in Federated Foundation Modelscited by 20
  7. 2024Unbridled Icarus: A Survey of the Potential Perils of Image Inputs in Multimodal Large Language Model Securitycited by 18
  8. 2025Are We Truly Forgetting? A Critical Re-examination of Machine Unlearning Evaluation Protocolscited by 16
  9. 2025NoT: Federated Unlearning via Weight Negationcited by 15
  10. 2024Unlearning during Learning: An Efficient Federated Machine Unlearning Methodcited by 14
  11. 2023QuickDrop: Efficient Federated Unlearning by Integrated Dataset Distillationcited by 11
  12. 2024Ferrari: Federated Feature Unlearning via Optimizing Feature Sensitivitycited by 11
38 more
  1. 2025ForgetMe: Evaluating Selective Forgetting in Generative Modelscited by 11
  2. 2025An Investigation into Value Misalignment in LLM-Generated Texts for Cultural Heritagecited by 8
  3. 2025Data Duplication: A Novel Multi-Purpose Attack Paradigm in Machine Unlearningcited by 8
  4. 2025Towards Reliable Forgetting: A Survey on Machine Unlearning Verificationcited by 8
  5. 2024Towards Efficient and Certified Recovery from Poisoning Attacks in Federated Learningcited by 7
  6. 2024Federated Unlearning: a Perspective of Stability and Fairnesscited by 7
  7. 2024A Survey on Recommendation Unlearning: Fundamentals, Taxonomy, Evaluation, and Open Questionscited by 7
  8. 2024Towards Privacy-Guaranteed Label Unlearning in Vertical Federated Learning: Few-Shot Forgetting without Disclosurecited by 5
  9. 2025Poisoning Attacks and Defenses to Federated Unlearningcited by 5
  10. 2025CoUn: Empowering Machine Unlearning via Contrastive Learningcited by 4
  11. 2024FedUHB: Accelerating Federated Unlearning via Polyak Heavy Ball Methodcited by 3
  12. 2024FedQUIT: On-Device Federated Unlearning via a Quasi-Competent Virtual Teachercited by 2
  13. 2024Efficient Federated Unlearning with Adaptive Differential Privacy Preservationcited by 2
  14. 2025Model Inversion Attack against Federated Unlearningcited by 2
  15. 2025Towards Efficient and Exact Forgetting Services in Pre-Trained-Model-based Continual Learningcited by 2
  16. 2025On the Security and Privacy of Federated Learning: A Survey with Attacks, Defenses, Frameworks, Applications, and Future Directionscited by 2
  17. 2026Certified Unlearning in Decentralized Federated Learningcited by 2
  18. 2025Federated Unlearning Made Practical: Seamless Integration via Negated Pseudo-Gradientscited by 1
  19. 2025BadFU: Backdoor Federated Learning through Adversarial Machine Unlearningcited by 1
  20. 2025ToFU: Transforming How Federated Learning Systems Forget User Datacited by 1
  21. 2025Fully Decentralized Certified Unlearningcited by 1
  22. 2025Feature-Selective Representation Misdirection for Machine Unlearningcited by 1
  23. 2025Certifying the Right to Be Forgotten: Primal-Dual Optimization for Sample and Label Unlearning in Vertical Federated Learningcited by 1
  24. 2026Causal Unlearning in Collaborative Optimization: Exact and Approximate Influence Reversal under Adversarial Contributionscited by 1
  25. 2024A Survey on Federated Unlearning: Challenges and Opportunitiescited by 0
  26. 2024Machine Unlearning with Minimal Gradient Dependence for High Unlearning Ratioscited by 0
  27. 2024Forgetting Through Transforming: Enabling Federated Unlearning via Class-Aware Representation Transformationcited by 0
  28. 2024Streamlined Federated Unlearning: Unite as One to Be Highly Efficientcited by 0
  29. 2024Federated Unlearning Model Recovery in Data with Skewed Label Distributionscited by 0
  30. 2025Sky of Unlearning (SoUL): Rewiring Federated Machine Unlearning via Selective Pruningcited by 0
  31. 2025DRAUN: An Algorithm-Agnostic Data Reconstruction Attack on Federated Unlearning Systemscited by 0
  32. 2025DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differencescited by 0
  33. 2025A Scenario-Oriented Survey of Federated Recommender Systems: Techniques, Challenges, and Future Directionscited by 0
  34. 2025Bringing Multi-Modal Multi-Task Federated Foundation Models to Education Domain: Prospects and Challengescited by 0
  35. 2025Towards Verifiable Federated Unlearning: Framework, Challenges, and The Road Aheadcited by 0
  36. 2025Dual-Phase Federated Deep Unlearning via Weight-Aware Rollback and Reconstructioncited by 0
  37. 2026Shadow Unlearning: A Neuro-Semantic Approach to Fidelity-Preserving Faceless Forgetting in LLMscited by 0
  38. 2026Lethe: Principled Dual-Stream Update for Persistent Knowledge Erasure in Federated Unlearningcited by 0

50 most cited of 58 All 58 (JSON)