mlsanityData to 7 Oct 2026

Position: Bridge the Gaps between Machine Unlearning and AI Regulation

arXiv 2502.12430 ↗First posted 18 Feb 2025cs.LG cs.AIcited by 5

On the map: LLM safety and security → Machine unlearning

Abstract (arXiv)

The ''right to be forgotten'' and the data privacy laws that encode it have motivated machine unlearning since its earliest days. Now, some argue that an inbound wave of artificial intelligence regulations -- like the European Union's Artificial Intelligence Act (AIA) -- may offer important new use cases for machine unlearning. However, this position paper argues, this opportunity will only be realized if researchers proactively bridge the (sometimes sizable) gaps between machine unlearning's state of the art and its potential applications to AI regulation. To demonstrate this point, we use the AIA as our primary case study. Specifically, we deliver a ``state of the union'' as regards machine unlearning's current potential (or, in many cases, lack thereof) for aiding compliance with various provisions of the AIA. This starts with a precise cataloging of the potential applications of machine unlearning to AIA compliance. For each, we flag the technical gaps that exist between the potential application and the state of the art of machine unlearning. Finally, we end with a call to action: for machine learning researchers to solve the open technical questions that could unlock machine unlearning's potential to assist compliance with the AIA -- and other AI regulations like it.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Placed in Machine unlearning, one of 12 directions in LLM safety and security. Builds on 65 of its 129 references that are in the map. First posted on arXiv 18 Feb 2025.

Builds on

65 of 129 references.

Closest ancestors · 34

Same direction, newest first

  1. 2024A Review on Machine Unlearning18 Nov
  2. 2024Machine Unlearning using Forgetting Neural Networks29 Oct
  3. 2024An Adversarial Perspective on Machine Unlearning for AI Safety26 Sep
  4. 2024On the Limitations and Prospects of Machine Unlearning for Generative AI1 Aug
  5. 2024MUSE: Machine Unlearning Six-Way Evaluation for Language Models8 Jul
  6. 2024UnUnlearning: Unlearning is not sufficient for content regulation in advanced generative AI27 Jun
  7. 2024Machine Unlearning Fails to Remove Data Poisoning Attacks25 Jun
  8. 2024Avoiding Copyright Infringement via Large Language Model Unlearning16 Jun
  9. 2024Don't Forget Too Much: Towards Machine Unlearning on Feature Level16 Jun
  10. 2024REVS: Unlearning Sensitive Information in Language Models via Rank Editing in the Vocabulary Space13 Jun
  11. 2024Are we making progress in unlearning? Findings from the first NeurIPS unlearning competition13 Jun
  12. 2024What makes unlearning hard and what to do about it3 Jun
22 more
  1. 2024Unlearning Climate Misinformation in Large Language Models29 May
  2. 2024Gone but Not Forgotten: Improved Benchmarks for Machine Unlearning29 May
  3. 2024Unlearning Information Bottleneck: Machine Unlearning of Systematic Patterns and Biases22 May
  4. 2024Machine Unlearning for Traditional Models and Large Language Models: A Short Survey1 Apr
  5. 2024Second-Order Information Matters: Revisiting Machine Unlearning for Large Language Models13 Mar
  6. 2024Machine Unlearning: Taxonomy, Metrics, Applications, Challenges, and Prospects13 Mar
  7. 2024Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacy2 Mar
  8. 2024Machine Unlearning of Pre-trained Large Language Models23 Feb
  9. 2024TOFU: A Task of Fictitious Unlearning for LLMs11 Jan
  10. 2023Unlearn What You Want to Forget: Efficient Unlearning for LLMs31 Oct
  11. 2023Breaking the Trilemma of Privacy, Utility, Efficiency via Controllable Machine Unlearning28 Oct
  12. 2023Fast Model Debias with Machine Unlearning19 Oct
  13. 2023Tight Bounds for Machine Unlearning via Differential Privacy2 Sep
  14. 2023Machine Unlearning: Solutions and Challenges14 Aug
  15. 2023Fair Machine Unlearning: Data Removal while Mitigating Disparities27 Jul
  16. 2023What can we learn from Data Leakage and Unlearning for Law?19 Jul
  17. 2023Machine Unlearning: its nature, scope, and importance for a "delete culture"24 May
  18. 2023Towards Unbounded Machine Unlearning20 Feb
  19. 2023To Be Forgotten or To Be Fair: Unveiling Fairness Implications of Machine Unlearning Methods7 Feb
  20. 2022An Introduction to Machine Unlearning2 Sep
  21. 2022Towards Adversarial Evaluations for Inexact Machine Unlearning17 Jan
  22. 2021On the Necessity of Auditable Algorithmic Definitions for Machine Unlearning22 Oct

Other references · 31

  1. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,409
  2. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,231
  3. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  4. 2019Machine Unlearningcited by 1,020
  5. 2023Extracting Training Data from Diffusion Modelscited by 723
  6. 2021BBQ: A Hand-Built Bias Benchmark for Question Answeringcited by 683
  7. 2019Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networkscited by 599
  8. 2019Making AI Forget You: Data Deletion in Machine Learningcited by 447
  9. 2020Amnesiac Machine Learningcited by 305
  10. 2020Data Poisoning Attacks Against Federated Learning Systemscited by 266
  11. 2020When Machine Unlearning Jeopardizes Privacycited by 181
  12. 2022The Privacy Onion Effect: Memorization is Relativecited by 128
19 more
  1. 2023Fairness And Bias in Artificial Intelligence: A Brief Survey of Sources, Impacts, And Mitigation Strategiescited by 83
  2. 2024Unlearning Concepts in Diffusion Model via Concept Domain Correction and Concept Preserving Gradientcited by 69
  3. 2023Connecting the Dots in Trustworthy Artificial Intelligence: From AI Principles, Ethics, and Key Requirements to Responsible AI Systems and Regulationcited by 60
  4. 2021Poison Forensics: Traceback of Data Poisoning Attacks in Neural Networkscited by 37
  5. 2024CopyBench: Measuring Literal and Non-Literal Reproduction of Copyright-Protected Text in Language Model Generationcited by 35
  6. 2024SHIELD: Evaluation and Defense Strategies for Copyright Compliance in LLM Text Generationcited by 33
  7. 2021ML Attack Models: Adversarial Attacks and Data Poisoning Attackscited by 23
  8. 2022Machine Learning Security against Data Poisoning: Are We There Yet?cited by 23
  9. 2024Data Attribution for Text-to-Image Models by Unlearning Synthesized Imagescited by 22
  10. 2024The Files are in the Computer: On Copyright, Memorization, and Generative AIcited by 20
  11. 2023Machine Unlearning in Learned Databases: An Experimental Analysiscited by 17
  12. 2023Bounding data reconstruction attacks with the hypothesis testing interpretation of differential privacycited by 14
  13. 2024Potion: Towards Poison Unlearningcited by 14
  14. 2023Measuring Bias in AI Models: An Statistical Approach Introducing N-Sigmacited by 11
  15. 2024A Dataset and Benchmark for Copyright Infringement Unlearning from Text-to-Image Diffusion Modelscited by 11
  16. 2024UNLEARN Efficient Removal of Knowledge in Large Language Modelscited by 9
  17. 2025Addressing Bias in Generative AI: Challenges and Research Opportunities in Information Managementcited by 7
  18. 2024Eternal Sunshine of the Mechanical Mind: The Irreconcilability of Machine Learning and the Right to be Forgottencited by 2
  19. 2024Operationalizing the Blueprint for an AI Bill of Rights: Recommendations for Practitioners, Researchers, and Policy Makerscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026Forget Many, Forget Right: Scalable and Precise Concept Unlearning in Diffusion Modelscited by 4
  2. 2026Computational Compliance for AI Regulation: Blueprint for a New Research Domaincited by 1
  3. 2026Forget-It-All: Multi-Concept Machine Unlearning via Concept-Aware Neuron Maskingcited by 1
  4. 2026Certified Per-Instance Unlearning Using Individual Sensitivity Boundscited by 0
  5. 2026An Investigation of the NeurIPS and ICML 2025 Position Trackscited by 0