mlsanityData to 13 Oct 2026

A Review on Machine Unlearning

arXiv 2411.11315 ↗First posted 18 Nov 2024cs.LGcited by 32

On the map: LLM safety and security → Machine unlearning

Abstract (arXiv)

Recently, an increasing number of laws have governed the useability of users' privacy. For example, Article 17 of the General Data Protection Regulation (GDPR), the right to be forgotten, requires machine learning applications to remove a portion of data from a dataset and retrain it if the user makes such a request. Furthermore, from the security perspective, training data for machine learning models, i.e., data that may contain user privacy, should be effectively protected, including appropriate erasure. Therefore, researchers propose various privacy-preserving methods to deal with such issues as machine unlearning. This paper provides an in-depth review of the security and privacy concerns in machine learning models. First, we present how machine learning can use users' private data in daily life and the role that the GDPR plays in this problem. Then, we introduce the concept of machine unlearning by describing the security threats in machine learning models and how to protect users' privacy from being violated using machine learning platforms. As the core content of the paper, we introduce and analyze current machine unlearning approaches and several representative research results and discuss them in the context of the data lineage. Furthermore, we also discuss the future research challenges in this field.

Key facts. Cited by 32 papers in the map (data through 13 Oct 2026). Placed in Machine unlearning, one of 12 directions in LLM safety and security. Builds on 38 of its 62 references that are in the map. First posted on arXiv 18 Nov 2024.

Builds on

38 of 62 references.

Closest ancestors · 10

Same direction, newest first

  1. 2022Deletion Inference, Reconstruction, and Compliance in Machine (Un)Learning7 Feb
  2. 2022Zero-Shot Machine Unlearning14 Jan
  3. 2021On the Necessity of Auditable Algorithmic Definitions for Machine Unlearning22 Oct
  4. 2021Unrolling SGD: Understanding Factors Influencing Machine Unlearning27 Sep
  5. 2021Hard to Forget: Poisoning Attacks on Certified Machine Unlearning17 Sep
  6. 2021Machine Unlearning of Features and Labels26 Aug
  7. 2021Certifiable Machine Unlearning for Linear Models29 Jun
  8. 2021A unified PAC-Bayesian framework for machine unlearning via information risk minimization1 Jun
  9. 2021DeepObliviate: A Powerful Charm for Erasing Data Residual Memory in Deep Neural Networks13 May
  10. 2021Machine Unlearning via Algorithmic Stability25 Feb

Other references · 28

  1. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,273
  2. 2017Understanding Black-box Predictions via Influence Functionscited by 1,729
  3. 2019Machine Unlearningcited by 1,056
  4. 2016Stealing Machine Learning Models via Prediction APIscited by 617
  5. 2019Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networkscited by 617
  6. 2019Certified Data Removal from Machine Learning Modelscited by 532
  7. 2019Making AI Forget You: Data Deletion in Machine Learningcited by 462
  8. 2014New insights and perspectives on the natural gradient methodcited by 438
  9. 2020Amnesiac Machine Learningcited by 319
  10. 2020Descent-to-Delete: Gradient-Based Methods for Machine Unlearningcited by 310
  11. 2019White-box vs Black-box: Bayes Optimal Strategies for Membership Inferencecited by 270
  12. 2020Approximate Data Deletion from Machine Learning Modelscited by 255
16 more
  1. 2020When Machine Unlearning Jeopardizes Privacycited by 198
  2. 2020Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observationscited by 180
  3. 2017Machine Learning Models that Remember Too Muchcited by 169
  4. 2020Mixed-Privacy Forgetting in Deep Networkscited by 163
  5. 2020DeltaGrad: Rapid retraining of machine learning modelscited by 149
  6. 2020Machine Unlearning for Random Forestscited by 131
  7. 2020Machine Unlearning: Linear Filtration for Logit-based Classifierscited by 95
  8. 2018Privacy Preserving Machine Learning: Threats and Solutionscited by 79
  9. 2019The relationship between trust in AI and trustworthy machine learning technologiescited by 78
  10. 2022Federated Unlearning with Knowledge Distillationcited by 73
  11. 2022Backdoor Defense with Machine Unlearningcited by 65
  12. 2018A Swiss Army Infinitesimal Jackknifecited by 52
  13. 2022Making Recommender Systems Forget: Learning and Unlearning for Erasable Recommendationcited by 29
  14. 2021Forget-SVGD: Particle-Based Bayesian Federated Unlearningcited by 16
  15. 2020COVI White Papercited by 4
  16. 2020Managing Data Lineage of O&G Machine Learning Models: The Sweet Spot for Shale Use Casecited by 2

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2024: 1; 2025: 21; 2026: 10.

32 papers.

Sort:

By area:

  1. 2025Unlearning through Knowledge Overwriting: Reversible Federated Unlearning via Selective Sparse Adaptercited by 15
  2. 2025Towards Reliable Forgetting: A Survey on Machine Unlearning Verificationcited by 8
  3. 2026Forget Many, Forget Right: Scalable and Precise Concept Unlearning in Diffusion Modelscited by 7
  4. 2026RAZOR: Ratio-Aware Layer Editing for Targeted Unlearning in Vision Transformers and Diffusion Modelscited by 7
  5. 2025Position: Bridge the Gaps between Machine Unlearning and AI Regulationcited by 6
  6. 2026FG-OrIU: Towards Better Forgetting via Feature-Gradient Orthogonality for Incremental Unlearningcited by 6
  7. 2025A Survey on Unlearnable Datacited by 5
  8. 2025Machine Learners Should Acknowledge the Legal Implications of Large Language Models as Personal Datacited by 4
  9. 2025Deep Contrastive Unlearning for Language Modelscited by 4
  10. 2025RecPS: Privacy Risk Scoring for Recommender Systemscited by 4
  11. 2025Unlearning Comparator: A Visual Analytics System for Comparative Evaluation of Machine Unlearning Methodscited by 4
  12. 2025Geometric-disentangelment Unlearningcited by 4
20 more
  1. 2024Learning to Forget using Hypernetworkscited by 3
  2. 2025Enabling Group Fairness in Graph Unlearning via Bi-level Debiasingcited by 3
  3. 2025AMCR: A Framework for Assessing and Mitigating Copyright Risks in Generative Modelscited by 3
  4. 2026Forget-It-All: Multi-Concept Machine Unlearning via Concept-Aware Neuron Maskingcited by 3
  5. 2025How does Bayesian Sampling help Membership Inference Attacks?cited by 2
  6. 2025Evaluating the Defense Potential of Machine Unlearning against Membership Inference Attackscited by 2
  7. 2025Sealing The Backdoor: Unlearning Adversarial Text Triggers In Diffusion Models Using Knowledge Distillationcited by 2
  8. 2025BadFU: Backdoor Federated Learning through Adversarial Machine Unlearningcited by 1
  9. 2025Analise de Desaprendizado de Maquina em Modelos de Classificacao de Imagens Medicascited by 1
  10. 2025Machine Unlearning for Responsible and Adaptive AI in Educationcited by 1
  11. 2025SUGAR: A Sweeter Spot for Generative Unlearning of Many Identitiescited by 1
  12. 2025Data Augmentation Improves Machine Unlearningcited by 0
  13. 2025Selective Forgetting in Option Calibration: An Operator-Theoretic Gauss-Newton Frameworkcited by 0
  14. 2025Supervised Contrastive Machine Unlearning of Background Bias in Sonar Image Classification with Fine-Grained Explainable AIcited by 0
  15. 2026Relationship-Aware Safety Unlearning for Multimodal LLMscited by 0
  16. 2026Understanding U.S. Users' Security and Privacy Transparency Needs for Consumer-Facing Generative AIcited by 0
  17. 2026Does Machine Unlearning Preserve Clinical Safety? A Risk Analysis for Medical Image Classificationcited by 0
  18. 2026LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threatscited by 0
  19. 2026Repurposing Obsolete Representations for Post-Deployment Adaptationcited by 0
  20. 2026No Concept Escapes the Audit: Auditing-Aware Unlearning for Verifiable Concept Erasure in Diffusion Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024A Survey on Machine Unlearning: Techniques and New Emerged Privacy Risks
  2. 2023Learn to Unlearn: A Survey on Machine Unlearning
  3. 2024Machine Unlearning: Taxonomy, Metrics, Applications, Challenges, and Prospects
  4. 2022A Survey of Machine Unlearning
  5. 2023Machine Unlearning: Solutions and Challenges
  6. 2024Machine Unlearning: A Comprehensive Survey
  7. 2025How Secure is Forgetting? Linking Machine Unlearning to Machine Learning Attacks
  8. 2024Silver Linings in the Shadows: Harnessing Membership Inference for Machine Unlearning