mlsanityData to 7 Oct 2026

Towards Unbounded Machine Unlearning

arXiv 2302.09880 ↗First posted 20 Feb 2023cs.LG cs.CRcited by 261

On the map: LLM safety and security → Machine unlearning

Abstract (arXiv)

Deep machine unlearning is the problem of `removing' from a trained neural network a subset of its training set. This problem is very timely and has many applications, including the key tasks of removing biases (RB), resolving confusion (RC) (caused by mislabelled data in trained models), as well as allowing users to exercise their `right to be forgotten' to protect User Privacy (UP). This paper is the first, to our knowledge, to study unlearning for different applications (RB, RC, UP), with the view that each has its own desiderata, definitions for `forgetting' and associated metrics for forget quality. For UP, we propose a novel adaptation of a strong Membership Inference Attack for unlearning. We also propose SCRUB, a novel unlearning algorithm, which is the only method that is consistently a top performer for forget quality across the different application-dependent metrics for RB, RC, and UP. At the same time, SCRUB is also consistently a top performer on metrics that measure model utility (i.e. accuracy on retained data and generalization), and is more efficient than previous work. The above are substantiated through a comprehensive empirical evaluation against previous state-of-the-art.

Key facts. Cited by 261 papers in the map (data through 7 Oct 2026). Placed in Machine unlearning, one of 12 directions in LLM safety and security. Builds on 34 of its 44 references that are in the map. First posted on arXiv 20 Feb 2023.

Builds on

34 of 44 references.

Closest ancestors · 4

Same direction, newest first

  1. 2022Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks using an Incompetent Teacher17 May
  2. 2021On the Necessity of Auditable Algorithmic Definitions for Machine Unlearning22 Oct
  3. 2021Unrolling SGD: Understanding Factors Influencing Machine Unlearning27 Sep
  4. 2021Remember What You Want to Forget: Algorithms for Machine Unlearning4 Mar

Other references · 30

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  5. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  6. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  7. 2016Deep Learning with Differential Privacycited by 2,682
  8. 2018Neural Tangent Kernel: Convergence and Generalization in Neural Networkscited by 2,597
  9. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  10. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,313
  11. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,304
  12. 2019Machine Unlearningcited by 1,020
18 more
  1. 2014Striving for Simplicity: The All Convolutional Netcited by 983
  2. 2017A Closer Look at Memorization in Deep Networkscited by 936
  3. 2021Membership Inference Attacks From First Principlescited by 839
  4. 2019Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networkscited by 599
  5. 2019Certified Data Removal from Machine Learning Modelscited by 512
  6. 2019Making AI Forget You: Data Deletion in Machine Learningcited by 447
  7. 2021Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarkscited by 388
  8. 2020Amnesiac Machine Learningcited by 305
  9. 2020Descent-to-Delete: Gradient-Based Methods for Machine Unlearningcited by 303
  10. 2020Approximate Data Deletion from Machine Learning Modelscited by 250
  11. 2019The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networkscited by 241
  12. 2018Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learningcited by 219
  13. 2020When Machine Unlearning Jeopardizes Privacycited by 181
  14. 2020On Hyperparameter Optimization of Machine Learning Algorithms: Theory and Practicecited by 181
  15. 2020Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observationscited by 171
  16. 2020Mixed-Privacy Forgetting in Deep Networkscited by 158
  17. 2021A Survey on Bias in Visual Datasetscited by 84
  18. 2022Federated Unlearning with Knowledge Distillationcited by 70

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 6; 2024: 90; 2025: 87; 2026: 78.

261 papers.

Sort:

By area:

  1. 2024TOFU: A Task of Fictitious Unlearning for LLMscited by 507
  2. 2024The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearningcited by 488
  3. 2024Rethinking Machine Unlearning for Large Language Modelscited by 247
  4. 2023In-Context Unlearning: Language Models as Few Shot Unlearnerscited by 214
  5. 2024Large Language Model Unlearning via Embedding-Corrupted Promptscited by 112
  6. 2024What makes unlearning hard and what to do about itcited by 89
  7. 2024Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearningcited by 81
  8. 2024Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacycited by 78
  9. 2024RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Modelscited by 77
  10. 2025Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyondcited by 76
  11. 2024LLM Unlearning via Loss Adjustment with Only Forget Datacited by 71
  12. 2024Machine Unlearning for Image-to-Image Generative Modelscited by 47
38 more
  1. 2024UnUnlearning: Unlearning is not sufficient for content regulation in advanced generative AIcited by 46
  2. 2024Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearningcited by 44
  3. 2024Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancementcited by 43
  4. 2024To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language Modelscited by 42
  5. 2024Dissecting Language Models: Machine Unlearning via Selective Pruningcited by 38
  6. 2025LLM Unlearning via Neural Activation Redirectioncited by 38
  7. 2024Machine Unlearning Fails to Remove Data Poisoning Attackscited by 35
  8. 2024Erasing Conceptual Knowledge from Language Modelscited by 34
  9. 2024Continual Forgetting for Pre-trained Vision Modelscited by 29
  10. 2024Towards Certified Unlearning for Deep Neural Networkscited by 28
  11. 2025Decoupled Distillation to Erase: A General Unlearning Method for Any Class-centric Taskscited by 28
  12. 2024Corrective Machine Unlearningcited by 26
  13. 2024Towards Scalable Exact Machine Unlearning Using Parameter-Efficient Fine-Tuningcited by 25
  14. 2024WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Modelscited by 25
  15. 2025Certified Unlearning for Neural Networkscited by 25
  16. 2024Unified Parameter-Efficient Unlearning for LLMscited by 24
  17. 2023Deep Unlearning: Fast and Efficient Gradient-free Approach to Class Forgettingcited by 21
  18. 2025SAEs Can Improve Unlearning: Dynamic Sparse Autoencoder Guardrails for Precision Unlearning in LLMscited by 21
  19. 2024The Utility and Complexity of in- and out-of-Distribution Machine Unlearningcited by 20
  20. 2024Learning to Unlearn for Robust Machine Unlearningcited by 19
  21. 2025Learning to Unlearn while Retaining: Combating Gradient Conflicts in Machine Unlearningcited by 19
  22. 2024Label-Agnostic Forgetting: A Supervision-Free Unlearning in Deep Modelscited by 18
  23. 2024Is Retain Set All You Need in Machine Unlearning? Restoring Performance of Unlearned Models with Out-Of-Distribution Imagescited by 18
  24. 2024Attribute-to-Delete: Machine Unlearning via Datamodel Matchingcited by 18
  25. 2024Rewind-to-Delete: Certified Machine Unlearning for Nonconvex Functionscited by 17
  26. 2024MUNBa: Machine Unlearning via Nash Bargainingcited by 17
  27. 2025Tool Unlearning for Tool-Augmented LLMscited by 17
  28. 2023Reinforcement Unlearningcited by 16
  29. 2024Adversarial Machine Unlearningcited by 16
  30. 2024MU-Bench: A Multitask Multimodal Benchmark for Machine Unlearningcited by 16
  31. 2024Targeted Unlearning with Single Layer Unlearning Gradientcited by 16
  32. 2025Are We Truly Forgetting? A Critical Re-examination of Machine Unlearning Evaluation Protocolscited by 16
  33. 2024An Information Theoretic Approach to Machine Unlearningcited by 15
  34. 2025Sculpting Memory: Multi-Concept Forgetting in Diffusion Models via Dynamic Mask and Concept-Aware Optimizationcited by 15
  35. 2024Potion: Towards Poison Unlearningcited by 14
  36. 2024Unstable Unlearning: The Hidden Risk of Concept Resurgence in Diffusion Modelscited by 14
  37. 2023DUCK: Distance-based Unlearning via Centroid Kinematicscited by 13
  38. 2024Federated Learning Priorities Under the European Union Artificial Intelligence Actcited by 13

50 most cited of 261 All 261 (JSON)