mlsanityData to 7 Oct 2026

Formalizing Data Deletion in the Context of the Right to be Forgotten

arXiv 2002.10635 ↗First posted 25 Feb 2020cs.CRcited by 46

Not on the map. Why?

Cited by 31 in LLM safety and security, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

The right of an individual to request the deletion of their personal data by an entity that might be storing it -- referred to as the right to be forgotten -- has been explicitly recognized, legislated, and exercised in several jurisdictions across the world, including the European Union, Argentina, and California. However, much of the discussion surrounding this right offers only an intuitive notion of what it means for it to be fulfilled -- of what it means for such personal data to be deleted. In this work, we provide a formal definitional framework for the right to be forgotten using tools and paradigms from cryptography. In particular, we provide a precise definition of what could be (or should be) expected from an entity that collects individuals' data when a request is made of it to delete some of this data. Our framework captures several, though not all, relevant aspects of typical systems involved in data processing. While it cannot be viewed as expressing the statements of current laws (especially since these are rather vague in this respect), our work offers technically precise definitions that represent possibilities for what the law could reasonably expect, and alternatives for what future versions of the law could explicitly require. Finally, with the goal of demonstrating the applicability of our framework and definitions, we consider various natural and simple scenarios where the right to be forgotten comes up. For each of these scenarios, we highlight the pitfalls that arise even in genuine attempts at implementing systems offering deletion guarantees, and also describe technological solutions that provably satisfy our definitions. These solutions bring together techniques built by various communities.

Key facts. Cited by 46 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 7; 2023: 9; 2024: 12; 2025: 6; 2026: 4.

46 papers.

Sort:

By area:

  1. 2021Remember What You Want to Forget: Algorithms for Machine Unlearningcited by 360
  2. 2022A Survey of Machine Unlearningcited by 298
  3. 2021Fast Yet Effective Machine Unlearningcited by 209
  4. 2024A Comprehensive Study of Knowledge Editing for Large Language Modelscited by 157
  5. 2024Machine Unlearning of Pre-trained Large Language Modelscited by 118
  6. 2023Machine Unlearning: Solutions and Challengescited by 85
  7. 2024Position: LLM Unlearning Benchmarks are Weak Measures of Progresscited by 58
  8. 2021Survey: Leakage and Privacy at Inference Timecited by 44
  9. 2023Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomycited by 44
  10. 2023Training Data Extraction From Pre-trained Language Models: A Surveycited by 43
  11. 2022Algorithms that Approximate Data Removal: New Results and Limitationscited by 39
  12. 2023Knowledge Sanitization of Large Language Modelscited by 34
34 more
  1. 2024Machine Unlearning: A Comprehensive Surveycited by 33
  2. 2021SSSE: Efficiently Erasing Samples from Trained Machine Learning Modelscited by 28
  3. 2022Markov Chain Monte Carlo-Based Machine Unlearning: Unlearning What Needs to be Forgottencited by 25
  4. 2022Verifiable and Provably Secure Machine Unlearningcited by 24
  5. 2024Reconstruction Attacks on Machine Unlearning: Simple Models are Vulnerablecited by 24
  6. 2022Knowledge Removal in Sampling-based Bayesian Inferencecited by 20
  7. 2021DeepObliviate: A Powerful Charm for Erasing Data Residual Memory in Deep Neural Networkscited by 19
  8. 2022Deletion Inference, Reconstruction, and Compliance in Machine (Un)Learningcited by 19
  9. 2023Machine Unlearning: A Surveycited by 18
  10. 2023Tight Bounds for Machine Unlearning via Differential Privacycited by 18
  11. 2025Unlearning through Knowledge Overwriting: Reversible Federated Unlearning via Selective Sparse Adaptercited by 15
  12. 2021Reviving Purpose Limitation and Data Minimisation in Data-Driven Systemscited by 11
  13. 2023Information Flow Control in Machine Learning through Modular Model Architecturecited by 11
  14. 2024Ferrari: Federated Feature Unlearning via Optimizing Feature Sensitivitycited by 11
  15. 2025Distillation Robustifies Unlearningcited by 11
  16. 2023Towards Bridging the Gaps between the Right to Explanation and the Right to be Forgottencited by 10
  17. 2023Ticketed Learning-Unlearning Schemescited by 10
  18. 2021Bayesian Inference Forgettingcited by 7
  19. 2024Towards Privacy-Guaranteed Label Unlearning in Vertical Federated Learning: Few-Shot Forgetting without Disclosurecited by 5
  20. 2024Toward Efficient Data-Free Unlearningcited by 4
  21. 2021Burn After Reading: Online Adaptation for Cross-domain Streaming Datacited by 3
  22. 2024Quantifying Memorization and Detecting Training Data of Pre-trained Language Models using Japanese Newspapercited by 2
  23. 2024Data Deletion for Linear Regression with Noisy SGDcited by 2
  24. 2025Improving Unlearning with Model Updates Probably Aligned with Gradientscited by 1
  25. 2025Robust MLLM Unlearning via Visual Knowledge Distillationcited by 1
  26. 2026Protecting the Undeleted in Machine Unlearningcited by 1
  27. 2026Unlearning Evaluation through Subset Statistical Independencecited by 1
  28. 2022Debugging using Orthogonal Gradient Descentcited by 0
  29. 2024Online Algorithms with Limited Data Retentioncited by 0
  30. 2024Towards Aligned Data Removal via Twin Machine Unlearningcited by 0
  31. 2025Towards Aligned Data Forgetting via Twin Machine Unlearningcited by 0
  32. 2025Memorizing Long-tail Data Can Help Generalization Through Compositioncited by 0
  33. 2026Lethe: Principled Dual-Stream Update for Persistent Knowledge Erasure in Federated Unlearningcited by 0
  34. 2026A Model Merging Approach for Continual MLLM Unlearningcited by 0