Formalizing Data Deletion in the Context of the Right to be Forgotten
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
Citing papers per year: 2021: 8; 2022: 7; 2023: 9; 2024: 12; 2025: 6; 2026: 4.
46 papers.
Sort:
By area:
- 2021Remember What You Want to Forget: Algorithms for Machine Unlearningcited by 360
- 2022A Survey of Machine Unlearningcited by 298
- 2021Fast Yet Effective Machine Unlearningcited by 209
- 2024A Comprehensive Study of Knowledge Editing for Large Language Modelscited by 157
- 2024Machine Unlearning of Pre-trained Large Language Modelscited by 118
- 2023Machine Unlearning: Solutions and Challengescited by 85
- 2024Position: LLM Unlearning Benchmarks are Weak Measures of Progresscited by 58
- 2021Survey: Leakage and Privacy at Inference Timecited by 44
- 2023Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomycited by 44
- 2023Training Data Extraction From Pre-trained Language Models: A Surveycited by 43
- 2022Algorithms that Approximate Data Removal: New Results and Limitationscited by 39
- 2023Knowledge Sanitization of Large Language Modelscited by 34
34 more
- 2024Machine Unlearning: A Comprehensive Surveycited by 33
- 2021SSSE: Efficiently Erasing Samples from Trained Machine Learning Modelscited by 28
- 2022Markov Chain Monte Carlo-Based Machine Unlearning: Unlearning What Needs to be Forgottencited by 25
- 2022Verifiable and Provably Secure Machine Unlearningcited by 24
- 2024Reconstruction Attacks on Machine Unlearning: Simple Models are Vulnerablecited by 24
- 2022Knowledge Removal in Sampling-based Bayesian Inferencecited by 20
- 2021DeepObliviate: A Powerful Charm for Erasing Data Residual Memory in Deep Neural Networkscited by 19
- 2022Deletion Inference, Reconstruction, and Compliance in Machine (Un)Learningcited by 19
- 2023Machine Unlearning: A Surveycited by 18
- 2023Tight Bounds for Machine Unlearning via Differential Privacycited by 18
- 2025Unlearning through Knowledge Overwriting: Reversible Federated Unlearning via Selective Sparse Adaptercited by 15
- 2021Reviving Purpose Limitation and Data Minimisation in Data-Driven Systemscited by 11
- 2023Information Flow Control in Machine Learning through Modular Model Architecturecited by 11
- 2024Ferrari: Federated Feature Unlearning via Optimizing Feature Sensitivitycited by 11
- 2025Distillation Robustifies Unlearningcited by 11
- 2023Towards Bridging the Gaps between the Right to Explanation and the Right to be Forgottencited by 10
- 2023Ticketed Learning-Unlearning Schemescited by 10
- 2021Bayesian Inference Forgettingcited by 7
- 2024Towards Privacy-Guaranteed Label Unlearning in Vertical Federated Learning: Few-Shot Forgetting without Disclosurecited by 5
- 2024Toward Efficient Data-Free Unlearningcited by 4
- 2021Burn After Reading: Online Adaptation for Cross-domain Streaming Datacited by 3
- 2024Quantifying Memorization and Detecting Training Data of Pre-trained Language Models using Japanese Newspapercited by 2
- 2024Data Deletion for Linear Regression with Noisy SGDcited by 2
- 2025Improving Unlearning with Model Updates Probably Aligned with Gradientscited by 1
- 2025Robust MLLM Unlearning via Visual Knowledge Distillationcited by 1
- 2026Protecting the Undeleted in Machine Unlearningcited by 1
- 2026Unlearning Evaluation through Subset Statistical Independencecited by 1
- 2022Debugging using Orthogonal Gradient Descentcited by 0
- 2024Online Algorithms with Limited Data Retentioncited by 0
- 2024Towards Aligned Data Removal via Twin Machine Unlearningcited by 0
- 2025Towards Aligned Data Forgetting via Twin Machine Unlearningcited by 0
- 2025Memorizing Long-tail Data Can Help Generalization Through Compositioncited by 0
- 2026Lethe: Principled Dual-Stream Update for Persistent Knowledge Erasure in Federated Unlearningcited by 0
- 2026A Model Merging Approach for Continual MLLM Unlearningcited by 0
- 2026A Model Merging Approach for Continual MLLM Unlearning5 Aug 2026
- 2026Unlearning Evaluation through Subset Statistical Independence28 Feb 2026
- 2026Protecting the Undeleted in Machine Unlearning18 Feb 2026
- 2026Lethe: Principled Dual-Stream Update for Persistent Knowledge Erasure in Federated Unlearning30 Jan 2026
- 2025Robust MLLM Unlearning via Visual Knowledge Distillation12 Dec 2025
- 2025Improving Unlearning with Model Updates Probably Aligned with Gradients4 Nov 2025
- 2025Memorizing Long-tail Data Can Help Generalization Through Composition18 Oct 2025
- 2025Distillation Robustifies Unlearning6 Jun 2025
- 2025Unlearning through Knowledge Overwriting: Reversible Federated Unlearning via Selective Sparse Adapter28 Feb 2025
- 2025Towards Aligned Data Forgetting via Twin Machine Unlearning15 Jan 2025
- 2024Toward Efficient Data-Free Unlearning18 Dec 2024
- 2024Towards Privacy-Guaranteed Label Unlearning in Vertical Federated Learning: Few-Shot Forgetting without Disclosure14 Oct 2024
34 more
- 2024Data Deletion for Linear Regression with Noisy SGD12 Oct 2024
- 2024Position: LLM Unlearning Benchmarks are Weak Measures of Progress3 Oct 2024
- 2024Towards Aligned Data Removal via Twin Machine Unlearning21 Aug 2024
- 2024Reconstruction Attacks on Machine Unlearning: Simple Models are Vulnerable30 May 2024
- 2024Ferrari: Federated Feature Unlearning via Optimizing Feature Sensitivity23 May 2024
- 2024Machine Unlearning: A Comprehensive Survey13 May 2024
- 2024Quantifying Memorization and Detecting Training Data of Pre-trained Language Models using Japanese Newspaper26 Apr 2024
- 2024Online Algorithms with Limited Data Retention17 Apr 2024
- 2024Machine Unlearning of Pre-trained Large Language Models23 Feb 2024
- 2024A Comprehensive Study of Knowledge Editing for Large Language Models2 Jan 2024
- 2023Knowledge Sanitization of Large Language Models21 Sep 2023
- 2023Tight Bounds for Machine Unlearning via Differential Privacy2 Sep 2023
- 2023Machine Unlearning: Solutions and Challenges14 Aug 2023
- 2023Ticketed Learning-Unlearning Schemes27 Jun 2023
- 2023Machine Unlearning: A Survey6 Jun 2023
- 2023Information Flow Control in Machine Learning through Modular Model Architecture5 Jun 2023
- 2023Training Data Extraction From Pre-trained Language Models: A Survey25 May 2023
- 2023Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomy10 May 2023
- 2023Towards Bridging the Gaps between the Right to Explanation and the Right to be Forgotten8 Feb 2023
- 2022Verifiable and Provably Secure Machine Unlearning17 Oct 2022
- 2022Algorithms that Approximate Data Removal: New Results and Limitations25 Sep 2022
- 2022A Survey of Machine Unlearning6 Sep 2022
- 2022Debugging using Orthogonal Gradient Descent17 Jun 2022
- 2022Knowledge Removal in Sampling-based Bayesian Inference24 Mar 2022
- 2022Markov Chain Monte Carlo-Based Machine Unlearning: Unlearning What Needs to be Forgotten28 Feb 2022
- 2022Deletion Inference, Reconstruction, and Compliance in Machine (Un)Learning7 Feb 2022
- 2021Burn After Reading: Online Adaptation for Cross-domain Streaming Data8 Dec 2021
- 2021Fast Yet Effective Machine Unlearning17 Nov 2021
- 2021SSSE: Efficiently Erasing Samples from Trained Machine Learning Models8 Jul 2021
- 2021Survey: Leakage and Privacy at Inference Time4 Jul 2021
- 2021DeepObliviate: A Powerful Charm for Erasing Data Residual Memory in Deep Neural Networks13 May 2021
- 2021Remember What You Want to Forget: Algorithms for Machine Unlearning4 Mar 2021
- 2021Bayesian Inference Forgetting16 Jan 2021
- 2021Reviving Purpose Limitation and Data Minimisation in Data-Driven Systems15 Jan 2021
- 2021Remember What You Want to Forget: Algorithms for Machine Unlearningcited by 360
- 2022A Survey of Machine Unlearningcited by 298
- 2021Fast Yet Effective Machine Unlearningcited by 209
- 2024Machine Unlearning of Pre-trained Large Language Modelscited by 118
- 2023Machine Unlearning: Solutions and Challengescited by 85
- 2024Position: LLM Unlearning Benchmarks are Weak Measures of Progresscited by 58
- 2023Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomycited by 44
- 2022Algorithms that Approximate Data Removal: New Results and Limitationscited by 39
- 2024Machine Unlearning: A Comprehensive Surveycited by 33
- 2022Markov Chain Monte Carlo-Based Machine Unlearning: Unlearning What Needs to be Forgottencited by 25
- 2022Verifiable and Provably Secure Machine Unlearningcited by 24
- 2024Reconstruction Attacks on Machine Unlearning: Simple Models are Vulnerablecited by 24
12 most cited of 30 All 30 (JSON)
- 2026Unlearning Evaluation through Subset Statistical Independence28 Feb 2026
- 2026Protecting the Undeleted in Machine Unlearning18 Feb 2026
- 2026Lethe: Principled Dual-Stream Update for Persistent Knowledge Erasure in Federated Unlearning30 Jan 2026
- 2025Robust MLLM Unlearning via Visual Knowledge Distillation12 Dec 2025
- 2025Improving Unlearning with Model Updates Probably Aligned with Gradients4 Nov 2025
- 2025Distillation Robustifies Unlearning6 Jun 2025
- 2025Unlearning through Knowledge Overwriting: Reversible Federated Unlearning via Selective Sparse Adapter28 Feb 2025
- 2025Towards Aligned Data Forgetting via Twin Machine Unlearning15 Jan 2025
- 2024Toward Efficient Data-Free Unlearning18 Dec 2024
- 2024Towards Privacy-Guaranteed Label Unlearning in Vertical Federated Learning: Few-Shot Forgetting without Disclosure14 Oct 2024
- 2024Position: LLM Unlearning Benchmarks are Weak Measures of Progress3 Oct 2024
- 2024Towards Aligned Data Removal via Twin Machine Unlearning21 Aug 2024
12 newest of 30 All 30 (JSON)
- 2026A Model Merging Approach for Continual MLLM Unlearningcited by 0
- 2026A Model Merging Approach for Continual MLLM Unlearning5 Aug 2026
- 2024A Comprehensive Study of Knowledge Editing for Large Language Modelscited by 157
- 2021Survey: Leakage and Privacy at Inference Timecited by 44
- 2023Training Data Extraction From Pre-trained Language Models: A Surveycited by 43
- 2023Knowledge Sanitization of Large Language Modelscited by 34
- 2021SSSE: Efficiently Erasing Samples from Trained Machine Learning Modelscited by 28
- 2021Reviving Purpose Limitation and Data Minimisation in Data-Driven Systemscited by 11
- 2023Information Flow Control in Machine Learning through Modular Model Architecturecited by 11
- 2023Towards Bridging the Gaps between the Right to Explanation and the Right to be Forgottencited by 10
- 2021Bayesian Inference Forgettingcited by 7
- 2021Burn After Reading: Online Adaptation for Cross-domain Streaming Datacited by 3
- 2024Quantifying Memorization and Detecting Training Data of Pre-trained Language Models using Japanese Newspapercited by 2
- 2024Data Deletion for Linear Regression with Noisy SGDcited by 2
12 most cited of 15 All 15 (JSON)
- 2025Memorizing Long-tail Data Can Help Generalization Through Composition18 Oct 2025
- 2024Data Deletion for Linear Regression with Noisy SGD12 Oct 2024
- 2024Quantifying Memorization and Detecting Training Data of Pre-trained Language Models using Japanese Newspaper26 Apr 2024
- 2024Online Algorithms with Limited Data Retention17 Apr 2024
- 2024A Comprehensive Study of Knowledge Editing for Large Language Models2 Jan 2024
- 2023Knowledge Sanitization of Large Language Models21 Sep 2023
- 2023Information Flow Control in Machine Learning through Modular Model Architecture5 Jun 2023
- 2023Training Data Extraction From Pre-trained Language Models: A Survey25 May 2023
- 2023Towards Bridging the Gaps between the Right to Explanation and the Right to be Forgotten8 Feb 2023
- 2022Debugging using Orthogonal Gradient Descent17 Jun 2022
- 2021Burn After Reading: Online Adaptation for Cross-domain Streaming Data8 Dec 2021
- 2021SSSE: Efficiently Erasing Samples from Trained Machine Learning Models8 Jul 2021
12 newest of 15 All 15 (JSON)