# Control, Confidentiality, and the Right to be Forgotten

arXiv: https://arxiv.org/abs/2210.07876 · HTML: https://mlsanity.com/paper/2210.07876/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 18 of its 57 references that are in the map.
- First posted on arXiv 14 Oct 2022.

## Placed in

- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)

## Builds on (most cited first, 18 of 18)

- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks](https://mlsanity.com/paper/1911.04933/) (2019)
- [Certified Data Removal from Machine Learning Models](https://mlsanity.com/paper/1911.03030/) (2019)
- [Making AI Forget You: Data Deletion in Machine Learning](https://mlsanity.com/paper/1907.05012/) (2019)
- [Remember What You Want to Forget: Algorithms for Machine Unlearning](https://mlsanity.com/paper/2103.03279/) (2021)
- [Descent-to-Delete: Gradient-Based Methods for Machine Unlearning](https://mlsanity.com/paper/2007.02923/) (2020)
- [Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observations](https://mlsanity.com/paper/2003.02960/) (2020)
- [Adaptive Machine Unlearning](https://mlsanity.com/paper/2106.04378/) (2021)
- [On the Necessity of Auditable Algorithmic Definitions for Machine Unlearning](https://mlsanity.com/paper/2110.11891/) (2021)
- [Practical and Private (Deep) Learning without Sampling or Shuffling](https://mlsanity.com/paper/2103.00039/) (2021)
- [Machine Unlearning via Algorithmic Stability](https://mlsanity.com/paper/2102.13179/) (2021)
- [Algorithms that Remember: Model Inversion Attacks and Data Protection Law](https://mlsanity.com/paper/1807.04644/) (2018)
- [Formalizing Data Deletion in the Context of the Right to be Forgotten](https://mlsanity.com/paper/2002.10635/) (2020)
- [The Price of Differential Privacy under Continual Observation](https://mlsanity.com/paper/2112.00828/) (2021)
- [Max-Information, Differential Privacy, and Post-Selection Hypothesis Testing](https://mlsanity.com/paper/1604.03924/) (2016)
- [Linear Program Reconstruction in Practice](https://mlsanity.com/paper/1810.05692/) (2018)
- [Deletion-Compliance in the Absence of Privacy](https://mlsanity.com/paper/2201.03499/) (2022)

## Built on by (most cited first, 10 of 10)

- [Position: LLM Unlearning Benchmarks are Weak Measures of Progress](https://mlsanity.com/paper/2410.02879/) (2024)
- [Reconstruction Attacks on Machine Unlearning: Simple Models are Vulnerable](https://mlsanity.com/paper/2405.20272/) (2024)
- [Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy](https://mlsanity.com/paper/2410.09591/) (2024)
- [Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research](https://mlsanity.com/paper/2412.06966/) (2024)
- [Ticketed Learning-Unlearning Schemes](https://mlsanity.com/paper/2306.15744/) (2023)
- [Protecting the Undeleted in Machine Unlearning](https://mlsanity.com/paper/2602.16697/) (2026)
- [Example-based Explanations for Random Forests using Machine Unlearning](https://mlsanity.com/paper/2402.05007/) (2024)
- [Online Learning and Unlearning](https://mlsanity.com/paper/2505.08557/) (2025)
- [Online Algorithms with Limited Data Retention](https://mlsanity.com/paper/2404.10997/) (2024)
- [Modeling Deletion Requests in Machine Unlearning](https://mlsanity.com/paper/2610.04310/) (2026)

## Abstract (arXiv)

Recent digital rights frameworks give users the right to delete their data from systems that store and process their personal information (e.g., the "right to be forgotten" in the GDPR). How should deletion be formalized in complex systems that interact with many users and store derivative information? We argue that prior approaches fall short. Definitions of machine unlearning Cao and Yang [2015] are too narrowly scoped and do not apply to general interactive settings. The natural approach of deletion-as-confidentiality Garg et al. [2020] is too restrictive: by requiring secrecy of deleted data, it rules out social functionalities. We propose a new formalism: deletion-as-control. It allows users' data to be freely used before deletion, while also imposing a meaningful requirement after deletion--thereby giving users more control. Deletion-as-control provides new ways of achieving deletion in diverse settings. We apply it to social functionalities, and give a new unified view of various machine unlearning definitions from the literature. This is done by way of a new adaptive generalization of history independence. Deletion-as-control also provides a new approach to the goal of machine unlearning, that is, to maintaining a model while honoring users' deletion requests. We show that publishing a sequence of updated models that are differentially private under continual release satisfies deletion-as-control. The accuracy of such an algorithm does not depend on the number of deleted points, in contrast to the machine unlearning literature.