paper-with-me

홈 › Papers

Forget Unlearning: Towards True Data-Deletion in Machine Learning

2022-10-17 · Rishav Chourasia, Neil Shah

Unlearning algorithms aim to remove deleted data's influence from trained models at a cost lower than full retraining. However, prior guarantees of unlearning in literature are flawed and don't protect the privacy of deleted records. We show that when users delete their data as a function of published models, records in a database become interdependent. So, even retraining a fresh model after deletion of a record doesn't ensure its privacy. Secondly, unlearning algorithms that cache partial computations to speed up the processing can leak deleted information over a series of releases, violating the privacy of deleted records in the long run. To address these, we propose a sound deletion guarantee and show that the privacy of existing records is necessary for the privacy of deleted records. Under this notion, we propose an accurate, computationally efficient, and secure machine unlearning algorithm based on noisy gradient descent.

📄 PDF Abstract BibTeX arXiv:2210.08911

Code (0)

등록된 구현이 없습니다.

Tasks

Machine Unlearning

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Rethinking Machine Unlearning: Models Designed to Forget via Key Deletion

2026-03-16 · Sonia Laguna, Jorge da Silva Goncalves, Moritz Vandenhirtz, Alain Ryser 외 arxiv

Machine unlearning is rapidly becoming a practical requirement, driven by privacy regulations, data errors, and the need to remove harmful or corrupted training samples. Despite this, most existing methods tackle the pro…

Forgetting Has Neighbors: Localized Collateral Forgetting in Machine Unlearning

2026-05-29 · Polina Dolgova, Sebastian U. Stich arxiv

Machine unlearning aims to remove the influence of selected training examples without full retraining. Standard evaluations often summarize unlearning quality with aggregate metrics, such as accuracy- and forgetting-base…

Statistical Roughness-Informed Machine Unlearning

2026-02-10 · Mohammad Partohaghighi, Roummel Marcia, Bruce J. West, YangQuan Chen arxiv

Machine unlearning aims to remove the influence of a designated forget set from a trained model while preserving utility on the retained data. In modern deep networks, approximate unlearning frequently fails under large …

Graph-Guided Selective Unlearning for Language Models: Controlling Support Routes Beyond Forget Seeds

2026-08-27 · Waqas Khan, Tabinda Sarwar, Jingyue Cong, Xun Yi 외 arxiv

Enterprises fine-tune language models on proprietary data that may later require removal due to privacy, contractual, or compliance obligations. Selective unlearning removes requested knowledge while preserving model uti…

ICU-Bench:Benchmarking Continual Unlearning in Multimodal Large Language Models

2026-05-07 · Yuhang Wang, Wenjie Mei, Junkai Zhang, Guangyu He 외 arxiv

Although Multimodal Large Language Models (MLLMs) have achieved remarkable progress across many domains, their training on large-scale multimodal datasets raises serious privacy concerns, making effective machine unlearn…