mlsanityData to 7 Oct 2026

Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observations

arXiv 2003.02960 ↗First posted 5 Mar 2020cs.LG cs.CV cs.ITcited by 171

Not on the map. Why?

Cited by 149 in LLM safety and security, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We describe a procedure for removing dependency on a cohort of training data from a trained deep network that improves upon and generalizes previous methods to different readout functions and can be extended to ensure forgetting in the activations of the network. We introduce a new bound on how much information can be extracted per query about the forgotten cohort from a black-box network for which only the input-output behavior is observed. The proposed forgetting procedure has a deterministic part derived from the differential equations of a linearized version of the model, and a stochastic part that ensures information destruction by adding noise tailored to the geometry of the loss landscape. We exploit the connections between the activation and weight dynamics of a DNN inspired by Neural Tangent Kernels to compute the information in the activations.

Key facts. Cited by 171 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 17; 2023: 34; 2024: 58; 2025: 25; 2026: 26.

171 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. 2022A Survey of Machine Unlearningcited by 298
  4. 2021Unrolling SGD: Understanding Factors Influencing Machine Unlearningcited by 274
  5. 2023Towards Unbounded Machine Unlearningcited by 261
  6. 2024MUSE: Machine Unlearning Six-Way Evaluation for Language Modelscited by 251
  7. 2023In-Context Unlearning: Language Models as Few Shot Unlearnerscited by 214
  8. 2021Fast Yet Effective Machine Unlearningcited by 209
  9. 2022Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks using an Incompetent Teachercited by 189
  10. 2023Fast Machine Unlearning Without Retraining Through Selective Synaptic Dampeningcited by 177
  11. 2021Adaptive Machine Unlearningcited by 164
  12. 2021On the Necessity of Auditable Algorithmic Definitions for Machine Unlearningcited by 164
38 more
  1. 2023Boundary Unlearningcited by 132
  2. 2024Tamper-Resistant Safeguards for Open-Weight LLMscited by 132
  3. 2021Graph Unlearningcited by 129
  4. 2022Zero-Shot Machine Unlearningcited by 125
  5. 2021Federated Unlearning via Class-Discriminative Pruningcited by 108
  6. 2023KGA: A General Machine Unlearning Framework Based on Knowledge Gap Alignmentcited by 94
  7. 2022Federated Unlearning: How to Efficiently Erase a Client in FL?cited by 90
  8. 2023Machine Unlearning: Solutions and Challengescited by 85
  9. 2022Deep Unlearning via Randomized Conditionally Independent Hessianscited by 83
  10. 2022Towards Adversarial Evaluations for Inexact Machine Unlearningcited by 82
  11. 2023Circumventing Concept Erasure Methods For Text-to-Image Generative Modelscited by 81
  12. 2024Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacycited by 78
  13. 2024RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Modelscited by 77
  14. 2022Recommendation Unlearningcited by 71
  15. 2024Do Unlearning Methods Remove Information from Language Model Weights?cited by 66
  16. 2023Privacy Issues in Large Language Models: A Surveycited by 57
  17. 2024Scissorhands: Scrub Data Influence via Connection Sensitivity in Networkscited by 50
  18. 2024Machine Unlearning in Generative AI: A Surveycited by 49
  19. 2024Are we making progress in unlearning? Findings from the first NeurIPS unlearning competitioncited by 48
  20. 2021Hard to Forget: Poisoning Attacks on Certified Machine Unlearningcited by 47
  21. 2024Machine Unlearning for Image-to-Image Generative Modelscited by 47
  22. 2022ASIF: Coupled Data Turns Unimodal Models to Multimodal Without Trainingcited by 45
  23. 2021Survey: Leakage and Privacy at Inference Timecited by 44
  24. 2021Certifiable Machine Unlearning for Linear Modelscited by 42
  25. 2023Learn to Unlearn for Deep Neural Networks: Minimizing Unlearning Interference with Gradient Projectioncited by 37
  26. 2024Selective Forgetting: Advancing Machine Unlearning Techniques and Evaluation in Language Modelscited by 36
  27. 2024Machine Unlearning Fails to Remove Data Poisoning Attackscited by 35
  28. 2024Erasing Conceptual Knowledge from Language Modelscited by 34
  29. 2024Machine Unlearning: A Comprehensive Surveycited by 33
  30. 2022Deep Regression Unlearningcited by 32
  31. 2023Inductive Graph Unlearningcited by 30
  32. 2024A Review on Machine Unlearningcited by 30
  33. 2023Certified Minimax Unlearning with Generalization Rates and Deletion Capacitycited by 29
  34. 2021SSSE: Efficiently Erasing Samples from Trained Machine Learning Modelscited by 28
  35. 2023SAFE: Machine Unlearning With Shard Graphscited by 28
  36. 2023Towards Machine Unlearning Benchmarks: Forgetting the Personal Identities in Facial Recognition Systemscited by 27
  37. 2024Corrective Machine Unlearningcited by 26
  38. 2024Towards Scalable Exact Machine Unlearning Using Parameter-Efficient Fine-Tuningcited by 25

50 most cited of 171 All 171 (JSON)