paper-with-me

홈 › Papers

Tight Bounds for Machine Unlearning via Differential Privacy

2023-09-02 · Yiyang Huang, Clément L. Canonne

We consider the formulation of "machine unlearning" of Sekhari, Acharya, Kamath, and Suresh (NeurIPS 2021), which formalizes the so-called "right to be forgotten" by requiring that a trained model, upon request, should be able to "unlearn" a number of points from the training data, as if they had never been included in the first place. Sekhari et al. established some positive and negative results about the number of data points that can be successfully unlearnt by a trained model without impacting the model's accuracy (the "deletion capacity"), showing that machine unlearning could be achieved by using differentially private (DP) algorithms. However, their results left open a gap between upper and lower bounds on the deletion capacity of these algorithms: our work fully closes this gap, obtaining tight bounds on the deletion capacity achievable by DP-based machine unlearning algorithms.

📄 PDF Abstract BibTeX arXiv:2309.00886

Code (0)

등록된 구현이 없습니다.

Tasks

Machine Unlearning

Similar Papers 제목 키워드 기반

The Utility and Complexity of in- and out-of-Distribution Machine Unlearning

2024-12-12 · Youssef Allouah, Joshua Kazdan, Rachid Guerraoui, Sanmi Koyejo

Machine unlearning, the process of selectively removing data from trained models, is increasingly crucial for addressing privacy concerns and knowledge gaps post-deployment. Despite this importance, existing approaches a…

Machine Unlearning

Near-Optimal Pure Machine Unlearning for Smooth Strongly Convex Losses

2026-06-01 · Matthew Regehr, Gautam Kamath, Andrew Lowy arxiv

Machine unlearning is motivated by legal and user-facing requirements to remove the influence of individuals' data from trained models, such as the right to be forgotten. Prior work has developed algorithms and error bou…

Stochastic Optimization

Certified Per-Instance Unlearning Using Individual Sensitivity Bounds

2026-02-17 · Hanna Benarroch, Jamal Atif, Olivier Cappé arxiv

Certified machine unlearning can be achieved via noise injection leading to differential privacy guarantees, where noise is calibrated to worst-case sensitivity. Such conservative calibration often results in performance…

Auditing Approximate Machine Unlearning for Differentially Private Models

2025-08-26 · Yuechun Gu, Jiajie He, Keke Chen arxiv

Approximate machine unlearning aims to remove the effect of specific data from trained models to ensure individuals' privacy. Existing methods focus on the removed records and assume the retained ones are unaffected. How…

Data Augmentation

Adversarial Sample-Based Approach for Tighter Privacy Auditing in Final Model-Only Scenarios

2024-12-02 · Sangyeon Yoon, Wonje Jeung, Albert No

Auditing Differentially Private Stochastic Gradient Descent (DP-SGD) in the final model setting is challenging and often results in empirical lower bounds that are significantly looser than theoretical privacy guarantees…