mlsanityData to 14 Oct 2026

Machine Unlearning: A Survey

arXiv 2306.03558 ↗First posted 6 Jun 2023cs.CR cs.LGcited by 19

On the map: LLM safety and security → Machine unlearning

Abstract (arXiv)

Machine learning has attracted widespread attention and evolved into an enabling technology for a wide range of highly successful applications, such as intelligent computer vision, speech recognition, medical diagnosis, and more. Yet a special need has arisen where, due to privacy, usability, and/or the right to be forgotten, information about some specific samples needs to be removed from a model, called machine unlearning. This emerging technology has drawn significant interest from both academics and industry due to its innovation and practicality. At the same time, this ambitious problem has led to numerous research efforts aimed at confronting its challenges. To the best of our knowledge, no study has analyzed this complex topic or compared the feasibility of existing unlearning solutions in different kinds of scenarios. Accordingly, with this survey, we aim to capture the key concepts of unlearning techniques. The existing solutions are classified and summarized based on their characteristics within an up-to-date and comprehensive review of each category's advantages and limitations. The survey concludes by highlighting some of the outstanding issues with unlearning techniques, along with some feasible directions for new research opportunities.

Key facts. Cited by 19 papers in the map (data through 14 Oct 2026). Placed in Machine unlearning, one of 12 directions in LLM safety and security. Builds on 70 of its 129 references that are in the map. First posted on arXiv 6 Jun 2023.

Builds on

70 of 129 references.

Closest ancestors · 12

Same direction, newest first

  1. 2022A Survey of Machine Unlearning6 Sep
  2. 2022Zero-Shot Machine Unlearning14 Jan
  3. 2021Machine unlearning via GAN22 Nov
  4. 2021Fast Yet Effective Machine Unlearning17 Nov
  5. 2021On the Necessity of Auditable Algorithmic Definitions for Machine Unlearning22 Oct
  6. 2021Unrolling SGD: Understanding Factors Influencing Machine Unlearning27 Sep
  7. 2021Hard to Forget: Poisoning Attacks on Certified Machine Unlearning17 Sep
  8. 2021Machine Unlearning of Features and Labels26 Aug
  9. 2021Adaptive Machine Unlearning8 Jun
  10. 2021DeepObliviate: A Powerful Charm for Erasing Data Residual Memory in Deep Neural Networks13 May
  11. 2021Remember What You Want to Forget: Algorithms for Machine Unlearning4 Mar
  12. 2021Machine Unlearning via Algorithmic Stability25 Feb

Other references · 58

  1. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  2. 2018Neural Tangent Kernel: Convergence and Generalization in Neural Networkscited by 2,621
  3. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  4. 2020Extracting Training Data from Large Language Modelscited by 2,189
  5. 2017Understanding Black-box Predictions via Influence Functionscited by 1,741
  6. 2019Machine Unlearningcited by 1,061
  7. 2018The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networkscited by 864
  8. 2019Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networkscited by 618
  9. 2019Certified Data Removal from Machine Learning Modelscited by 535
  10. 2019Making AI Forget You: Data Deletion in Machine Learningcited by 465
  11. 2014New insights and perspectives on the natural gradient methodcited by 443
  12. 2019Federated Machine Learning: Concept and Applicationscited by 412
38 more
  1. 2018Adaptive Federated Learning in Resource Constrained Edge Computing Systemscited by 409
  2. 2019Federated Learning in Mobile Edge Networks: A Comprehensive Surveycited by 408
  3. 2020Amnesiac Machine Learningcited by 319
  4. 2020Descent-to-Delete: Gradient-Based Methods for Machine Unlearningcited by 311
  5. 2020Approximate Data Deletion from Machine Learning Modelscited by 255
  6. 2020When Machine Unlearning Jeopardizes Privacycited by 198
  7. 2020Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observationscited by 180
  8. 2020Mixed-Privacy Forgetting in Deep Networkscited by 163
  9. 2020DeltaGrad: Rapid retraining of machine learning modelscited by 149
  10. 2020Federated Learning for Internet of Things: Recent Advances, Taxonomy, and Open Challengescited by 139
  11. 2021Graph Unlearningcited by 138
  12. 2020Machine Unlearning for Random Forestscited by 131
  13. 2022The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retrainingcited by 118
  14. 2020Variational Bayesian Unlearningcited by 117
  15. 2021Federated Unlearning via Class-Discriminative Pruningcited by 115
  16. 2020When is Memorization of Irrelevant Training Data Necessary for High-Accuracy Learning?cited by 104
  17. 2020Machine Unlearning: Linear Filtration for Logit-based Classifierscited by 95
  18. 2020Graph Neural Networks Meet Neural-Symbolic Computing: A Survey and Perspectivecited by 95
  19. 2020Overcoming Catastrophic Forgetting in Graph Neural Networkscited by 95
  20. 2019Analyzing Information Leakage of Updates to Natural Language Modelscited by 90
  21. 2022Recommendation Unlearningcited by 80
  22. 2022Federated Unlearning with Knowledge Distillationcited by 73
  23. 2020DMCP: Differentiable Markov Channel Pruning for Neural Networkscited by 69
  24. 2022Backdoor Defense with Machine Unlearningcited by 65
  25. 2022PUMA: Performance Unchanged Model Augmentation for Training Data Removalcited by 58
  26. 2021Membership Inference Attacks Against Recommender Systemscited by 57
  27. 2018Algorithms that Remember: Model Inversion Attacks and Data Protection Lawcited by 55
  28. 2020Formalizing Data Deletion in the Context of the Right to be Forgottencited by 50
  29. 2020Towards Probabilistic Verification of Machine Unlearningcited by 50
  30. 2021Knowledge-aware Coupled Graph Neural Network for Social Recommendationcited by 49
  31. 2018Privacy-preserving Predictioncited by 48
  32. 2022Making Recommender Systems Forget: Learning and Unlearning for Erasable Recommendationcited by 29
  33. 2021Low-Latency Federated Learning over Wireless Channels with Differential Privacycited by 25
  34. 2020More Than Privacy: Applying Differential Privacy in Key Areas of Artificial Intelligencecited by 23
  35. 2020Near-Tight Margin-Based Generalization Bounds for Support Vector Machinescited by 19
  36. 2014Global Convergence of Online Limited Memory BFGScited by 18
  37. 2020Have you forgotten? A method to assess if machine learning models have forgotten datacited by 17
  38. 2020Exploration-Exploitation in Multi-Agent Learning: Catastrophe Theory Meets Game Theorycited by 17

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 7; 2025: 10; 2026: 1.

19 papers.

Sort:

By area:

  1. 2024Position: LLM Unlearning Benchmarks are Weak Measures of Progresscited by 63
  2. 2024Zero-Shot Class Unlearning in CLIP with Synthetic Samplescited by 17
  3. 2024A Survey on Machine Unlearning: Techniques and New Emerged Privacy Riskscited by 15
  4. 2024Deep Unlearn: Benchmarking Machine Unlearning for Image Classificationcited by 9
  5. 2024Edge Unlearning is Not "on Edge"! An Adaptive Exact Unlearning System on Resource-Constrained Devicescited by 9
  6. 2025FUNU: Boosting Machine Unlearning Efficiency by Filtering Unnecessary Unlearningcited by 7
  7. 2023Fast-NTK: Parameter-Efficient Unlearning for Large-Scale Modelscited by 5
  8. 2025Auditing Approximate Machine Unlearning for Differentially Private Modelscited by 4
  9. 2025Quantum-Inspired Audio Unlearning: Towards Privacy-Preserving Voice Biometricscited by 2
  10. 2025Machine Unlearning in Hyperbolic vs. Euclidean Multimodal Contrastive Learning: Adapting Alignment Calibration to MERUcited by 1
  11. 2025Efficient Machine Unlearning by Model Splitting and Core Sample Selectioncited by 1
  12. 2025EFU: Enforcing Federated Unlearning via Functional Encryptioncited by 1
7 more
  1. 2025Pre-Forgettable Models: Prompt Learning as a Native Mechanism for Unlearningcited by 1
  2. 2025Improving Unlearning with Model Updates Probably Aligned with Gradientscited by 1
  3. 2024Machine Unlearning using a Multi-GAN based Modelcited by 0
  4. 2024Machine Unlearning for Speaker-Agnostic Detection of Gender-Based Violence Condition in Speechcited by 0
  5. 2025Quotation-Based Data Retention Mechanism for Data Privacy in LLM-Empowered Network Servicescited by 0
  6. 2025Graph Unlearning: Efficient Node Removal in Graph Neural Networkscited by 0
  7. 2026Membership Inference Attacks for Retrieval Based In-Context Learning for Document Question Answeringcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022An Introduction to Machine Unlearning
  2. 2023Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomy
  3. 2024Machine Unlearning: Taxonomy, Metrics, Applications, Challenges, and Prospects
  4. 2026Forgetting Similar Samples: Can Machine Unlearning Do it Better?
  5. 2024A Comparative Study of Machine Unlearning Techniques for Image and Text Classification Models
  6. 2023Machine Unlearning: Solutions and Challenges
  7. 2024Machine Unlearning: A Comprehensive Survey
  8. 2023Learn to Unlearn: A Survey on Machine Unlearning