mlsanityData to 14 Oct 2026

Amnesiac Machine Learning

arXiv 2010.10981 ↗First posted 21 Oct 2020cs.LG cs.AI cs.CRcited by 319

Not on the map. Why?

Cited by 272 in LLM safety and security, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

The Right to be Forgotten is part of the recently enacted General Data Protection Regulation (GDPR) law that affects any data holder that has data on European Union residents. It gives EU residents the ability to request deletion of their personal data, including training records used to train machine learning models. Unfortunately, Deep Neural Network models are vulnerable to information leaking attacks such as model inversion attacks which extract class information from a trained model and membership inference attacks which determine the presence of an example in a model's training data. If a malicious party can mount an attack and learn private information that was meant to be removed, then it implies that the model owner has not properly protected their user's rights and their models may not be compliant with the GDPR law. In this paper, we present two efficient methods that address this question of how a model owner or data holder may delete personal data from models in such a way that they may not be vulnerable to model inversion and membership inference attacks while maintaining model efficacy. We start by presenting a real-world threat model that shows that simply removing training data is insufficient to protect users. We follow that up with two data removal methods, namely Unlearning and Amnesiac Unlearning, that enable model owners to protect themselves against such attacks while being compliant with regulations. We provide extensive empirical analysis that show that these methods are indeed efficient, safe to apply, effectively remove learned information about sensitive data from trained models while maintaining model efficacy.

Key facts. Cited by 319 papers in the map (data through 14 Oct 2026). First posted on arXiv 21 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 6; 2022: 21; 2023: 38; 2024: 106; 2025: 87; 2026: 61.

319 papers.

Sort:

By area:

  1. 2022Knowledge Unlearning for Mitigating Privacy Risks in Language Modelscited by 437
  2. 2023SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generationcited by 386
  3. 2022A Survey of Machine Unlearningcited by 312
  4. 2021Unrolling SGD: Understanding Factors Influencing Machine Unlearningcited by 279
  5. 2023Towards Unbounded Machine Unlearningcited by 268
  6. 2023In-Context Unlearning: Language Models as Few Shot Unlearnerscited by 224
  7. 2021Fast Yet Effective Machine Unlearningcited by 217
  8. 2023Model Sparsity Can Simplify Machine Unlearningcited by 214
  9. 2022Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks using an Incompetent Teachercited by 194
  10. 2023Fast Machine Unlearning Without Retraining Through Selective Synaptic Dampeningcited by 181
  11. 2021On the Necessity of Auditable Algorithmic Definitions for Machine Unlearningcited by 171
  12. 2023Emergent and Predictable Memorization in Large Language Modelscited by 148
38 more
  1. 2022The Privacy Onion Effect: Memorization is Relativecited by 136
  2. 2023Boundary Unlearningcited by 134
  3. 2022Zero-Shot Machine Unlearningcited by 133
  4. 2022Measuring Forgetting of Memorized Training Examplescited by 118
  5. 2021Federated Unlearning via Class-Discriminative Pruningcited by 115
  6. 2024SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearningcited by 104
  7. 2022Federated Unlearning: How to Efficiently Erase a Client in FL?cited by 95
  8. 2024What makes unlearning hard and what to do about itcited by 89
  9. 2022Towards Adversarial Evaluations for Inexact Machine Unlearningcited by 84
  10. 2024Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacycited by 82
  11. 2024LLM Unlearning via Loss Adjustment with Only Forget Datacited by 75
  12. 2023Learning to Unlearn: Instance-wise Unlearning for Pre-trained Classifierscited by 67
  13. 2023Right to be Forgotten in the Era of Large Language Models: Implications, Challenges, and Solutionscited by 60
  14. 2022PUMA: Performance Unchanged Model Augmentation for Training Data Removalcited by 58
  15. 2023Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomycited by 51
  16. 2024UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Modelscited by 50
  17. 2024Machine Unlearning for Image-to-Image Generative Modelscited by 47
  18. 2024Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancementcited by 45
  19. 2024Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearningcited by 44
  20. 2022Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attackscited by 43
  21. 2024To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language Modelscited by 43
  22. 2021Certifiable Machine Unlearning for Linear Modelscited by 42
  23. 2024Dissecting Language Models: Machine Unlearning via Selective Pruningcited by 42
  24. 2022Evaluating Machine Unlearning via Epistemic Uncertaintycited by 39
  25. 2024Machine Unlearning Fails to Remove Data Poisoning Attackscited by 37
  26. 2024Revisiting Who's Harry Potter: Towards Targeted Unlearning from a Causal Intervention Perspectivecited by 36
  27. 2024Machine Unlearning: A Comprehensive Surveycited by 35
  28. 2023A Duty to Forget, a Right to be Assured? Exposing Vulnerabilities in Machine Unlearning Servicescited by 34
  29. 2024Fast Exact Unlearning for In-Context Learning Data for LLMscited by 34
  30. 2024Alternate Preference Optimization for Unlearning Factual Knowledge in Large Language Modelscited by 33
  31. 2022Deep Regression Unlearningcited by 32
  32. 2024A Review on Machine Unlearningcited by 32
  33. 2023Inductive Graph Unlearningcited by 31
  34. 2022Making Recommender Systems Forget: Learning and Unlearning for Erasable Recommendationcited by 29
  35. 2023Certified Minimax Unlearning with Generalization Rates and Deletion Capacitycited by 29
  36. 2024Corrective Machine Unlearningcited by 29
  37. 2024Towards Scalable Exact Machine Unlearning Using Parameter-Efficient Fine-Tuningcited by 27
  38. 2025Certified Unlearning for Neural Networkscited by 27

50 most cited of 319 All 319 (JSON)