mlsanityData to 7 Oct 2026

Federated Unlearning: A Survey on Methods, Design Guidelines, and Evaluation Metrics

arXiv 2401.05146 ↗First posted 10 Jan 2024cs.LG cs.CRcited by 25

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

Abstract (arXiv)

Federated learning (FL) enables collaborative training of a machine learning (ML) model across multiple parties, facilitating the preservation of users' and institutions' privacy by maintaining data stored locally. Instead of centralizing raw data, FL exchanges locally refined model parameters to build a global model incrementally. While FL is more compliant with emerging regulations such as the European General Data Protection Regulation (GDPR), ensuring the right to be forgotten in this context - allowing FL participants to remove their data contributions from the learned model - remains unclear. In addition, it is recognized that malicious clients may inject backdoors into the global model through updates, e.g., to generate mispredictions on specially crafted data examples. Consequently, there is the need for mechanisms that can guarantee individuals the possibility to remove their data and erase malicious contributions even after aggregation, without compromising the already acquired "good" knowledge. This highlights the necessity for novel federated unlearning (FU) algorithms, which can efficiently remove specific clients' contributions without full model retraining. This article provides background concepts, empirical evidence, and practical guidelines to design/implement efficient FU schemes. This study includes a detailed analysis of the metrics for evaluating unlearning in FL and presents an in-depth literature review categorizing state-of-the-art FU contributions under a novel taxonomy. Finally, we outline the most relevant and still open technical challenges, by identifying the most promising research directions in the field.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Placed in Federated unlearning and poisoning, one of 12 directions in LLM safety and security. Builds on 61 of its 122 references that are in the map. First posted on arXiv 10 Jan 2024.

Builds on

61 of 122 references.

Closest ancestors · 14

Same direction, newest first

  1. 2023QuickDrop: Efficient Federated Unlearning by Integrated Dataset Distillation27 Nov
  2. 2023A Survey on Federated Unlearning: Challenges, Methods, and Future Directions31 Oct
  3. 2023FRAMU: Attention-based Machine Unlearning using Federated Reinforcement Learning19 Sep
  4. 2023Subspace based Federated Unlearning24 Feb
  5. 2023Heterogeneous Federated Knowledge Graph Embedding Learning and Unlearning4 Feb
  6. 2022Machine Unlearning of Federated Clusters28 Oct
  7. 2022Compressed Particle-Based Federated Bayesian Learning and Unlearning14 Sep
  8. 2022Federated Unlearning: How to Efficiently Erase a Client in FL?12 Jul
  9. 2022VeriFi: Towards Verifiable Federated Unlearning25 May
  10. 2022The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining14 Mar
  11. 2022Federated Unlearning with Knowledge Distillation24 Jan
  12. 2021Forget-SVGD: Particle-Based Bayesian Federated Unlearning23 Nov
2 more
  1. 2021Federated Unlearning via Class-Discriminative Pruning22 Oct
  2. 2021Bayesian Variational Federated Learning and Unlearning in Decentralized Networks8 Apr

Other references · 47

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
  4. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  5. 2017Understanding Black-box Predictions via Influence Functionscited by 1,714
  6. 2013Fine-Grained Visual Classification of Aircraftcited by 1,701
  7. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,052
  8. 2020Adaptive Federated Optimizationcited by 1,036
  9. 2019Deep Leakage from Gradientscited by 1,004
  10. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 836
  11. 2018LEAF: A Benchmark for Federated Settingscited by 780
  12. 2018How To Backdoor Federated Learningcited by 745
35 more
  1. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
  2. 2020A Survey on Knowledge Graphs: Representation, Acquisition and Applicationscited by 643
  3. 2019Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networkscited by 599
  4. 2021Federated Learning on Non-IID Data Silos: An Experimental Studycited by 566
  5. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 509
  6. 2016Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithmcited by 498
  7. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 479
  8. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 451
  9. 2020Flower: A Friendly Federated Learning Research Frameworkcited by 449
  10. 2017Measuring Catastrophic Forgetting in Neural Networkscited by 359
  11. 2019Differential Privacy Has Disparate Impact on Model Accuracycited by 316
  12. 2022A Survey of Machine Unlearningcited by 298
  13. 2018A Hybrid Approach to Privacy-Preserving Federated Learningcited by 208
  14. 2022Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks using an Incompetent Teachercited by 189
  15. 2020Mixed-Privacy Forgetting in Deep Networkscited by 158
  16. 2017A Survey on Homomorphic Encryption Schemes: Theory and Implementationcited by 154
  17. 2022Improving Generalization in Federated Learning by Seeking Flat Minimacited by 98
  18. 2021Preservation of the Global Knowledge by Not-True Distillation in Federated Learningcited by 87
  19. 2021Federated Reconstruction: Partially Local Federated Learningcited by 78
  20. 2018Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learningcited by 75
  21. 2020Differentially Private Secure Multi-Party Computation for Federated Learning in Financial Applicationscited by 58
  22. 2020Learn to Forget: Machine Unlearning via Neuron Maskingcited by 56
  23. 2022FedRecover: Recovering from Poisoning Attacks in Federated Learning using Historical Informationcited by 53
  24. 2020Multi-Participant Multi-Class Vertical Federated Learningcited by 47
  25. 2021Differentially Private Federated Knowledge Graphs Embeddingcited by 45
  26. 2022Federated Unlearning for On-Device Recommendationcited by 39
  27. 2020Federated Generalized Bayesian Learning via Distributed Stein Variational Gradient Descentcited by 34
  28. 2017Learning Differentially Private Recurrent Language Modelscited by 32
  29. 2023A Survey on Dataset Distillation: Approaches, Applications and Future Directionscited by 32
  30. 2022Knowledge Distillation for Federated Learning: a Practical Guidecited by 31
  31. 2022Membership Inference via Backdooringcited by 24
  32. 2023Get Rid Of Your Trail: Remotely Erasing Backdoors in Federated Learningcited by 12
  33. 2023Re-Weighted Softmax Cross-Entropy to Control Forgetting in Federated Learningcited by 9
  34. 2023Federated Learning Over Images: Vertical Decompositions and Pre-Trained Backbones Are Difficult to Beatcited by 4
  35. 2023Heterogeneous Decentralized Machine Unlearning with Seed Model Distillationcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 9; 2025: 9; 2026: 7.

25 papers.

Sort:

By area:

  1. 2024Threats, Attacks, and Defenses in Machine Unlearning: A Surveycited by 34
  2. 2024On Effects of Steering Latent Representation for Large Language Model Unlearningcited by 27
  3. 2025NoT: Federated Unlearning via Weight Negationcited by 15
  4. 2024Ferrari: Federated Feature Unlearning via Optimizing Feature Sensitivitycited by 11
  5. 2024Enable the Right to be Forgotten with Federated Client Unlearning in Medical Imagingcited by 9
  6. 2024How Data Inter-connectivity Shapes LLMs Unlearning: A Structural Unlearning Perspectivecited by 5
  7. 2024Towards Privacy-Guaranteed Label Unlearning in Vertical Federated Learning: Few-Shot Forgetting without Disclosurecited by 5
  8. 2026Parameter-Efficient Token Embedding Editing for Clinical Class-Level Unlearningcited by 3
  9. 2024FedQUIT: On-Device Federated Unlearning via a Quasi-Competent Virtual Teachercited by 2
  10. 2025Exploring Incremental Unlearning: Techniques, Challenges, and Future Directionscited by 2
  11. 2025Federated Unlearning Made Practical: Seamless Integration via Negated Pseudo-Gradientscited by 1
  12. 2025FedUP: Efficient Pruning-based Federated Unlearning for Model Poisoning Attackscited by 1
13 more
  1. 2025BadFU: Backdoor Federated Learning through Adversarial Machine Unlearningcited by 1
  2. 2024A Survey on Federated Unlearning: Challenges and Opportunitiescited by 0
  3. 2024Federated Unlearning Model Recovery in Data with Skewed Label Distributionscited by 0
  4. 2025Federated Graph Unlearningcited by 0
  5. 2025Tackling Federated Unlearning as a Parameter Estimation Problemcited by 0
  6. 2025Towards Verifiable Federated Unlearning: Framework, Challenges, and The Road Aheadcited by 0
  7. 2025Dual-Phase Federated Deep Unlearning via Weight-Aware Rollback and Reconstructioncited by 0
  8. 2026f-FUM: Federated Unlearning via min--max and f-divergencecited by 0
  9. 2026Asynchronous Federated Unlearning with Invariance Calibration for Medical Imagingcited by 0
  10. 2026pFedUL: Layer-Aware Federated Unlearning for Personalized Federated Learningcited by 0
  11. 2026When Unlearning Fails: Reliable Data Deletion under Post-Training in Agent Networkscited by 0
  12. 2026Lethe: How Hard Is It to Forget? A Benchmark for Federated Unlearning in Medical Imagingcited by 0
  13. 2026Dynamic Entanglement-Weighted Pruning for Quantum Federated Unlearning in Supply-Chain Risk Predictioncited by 0