paper-with-me

홈 › Papers

Gone but Not Forgotten: Improved Benchmarks for Machine Unlearning

2024-05-29 · Keltin Grimes, Collin Abidi, Cole Frank, Shannon Gallagher

Machine learning models are vulnerable to adversarial attacks, including attacks that leak information about the model's training data. There has recently been an increase in interest about how to best address privacy concerns, especially in the presence of data-removal requests. Machine unlearning algorithms aim to efficiently update trained models to comply with data deletion requests while maintaining performance and without having to resort to retraining the model from scratch, a costly endeavor. Several algorithms in the machine unlearning literature demonstrate some level of privacy gains, but they are often evaluated only on rudimentary membership inference attacks, which do not represent realistic threats. In this paper we describe and propose alternative evaluation methods for three key shortcomings in the current evaluation of unlearning algorithms. We show the utility of our alternative evaluations via a series of experiments of state-of-the-art unlearning algorithms on different computer vision datasets, presenting a more detailed picture of the state of the field.

📄 PDF Abstract BibTeX arXiv:2405.19211

Code (0)

등록된 구현이 없습니다.

Tasks

Machine Unlearning

Similar Papers 제목 키워드 기반

GONE: Structural Knowledge Unlearning via Neighborhood-Expanded Distribution Shaping

2026-02-21 · Chahana Dahal, Ashutosh Balasubramaniam, Zuobin Xiong arxiv

Unlearning knowledge is a pressing and challenging task in Large Language Models (LLMs) because of their unprecedented capability to memorize and digest training data at scale, raising more significant issues regarding s…

knowledge editing

Catastrophic Failure of LLM Unlearning via Quantization

2024-10-21 · Zhiwei Zhang, Fali Wang, Xiaomin Li, Zongyu Wu 외

Large language models (LLMs) have shown remarkable proficiency in generating text, benefiting from extensive training on vast textual corpora. However, LLMs may also acquire unwanted behaviors from the diverse and sensit…

Machine UnlearningQuantization

Conformal Unlearning: A New Paradigm for Unlearning in Conformal Predictors

2025-08-05 · Yahya Alkhatib, Muhammad Ahmar Jamal, Wee Peng Tay arxiv

Conformal unlearning aims to ensure that a trained conformal predictor miscovers data points with specific shared characteristics, such as those from a particular label class, associated with a specific user, or belongin…

REBEL: Hidden Knowledge Recovery via Evolutionary-Based Evaluation Loop

2026-02-05 · Patryk Rybak, Paweł Batorski, Paul Swoboda, Przemysław Spurek arxiv

Machine unlearning for LLMs aims to remove sensitive or copyrighted data from trained models. However, the true efficacy of current unlearning methods remains uncertain. Standard evaluation metrics rely on benign queries…

LegoNet: A Fast and Exact Unlearning Architecture

2022-10-28 · Sihao Yu, Fei Sun, Jiafeng Guo, Ruqing Zhang 외

Machine unlearning aims to erase the impact of specific training samples upon deleted requests from a trained model. Re-training the model on the retained data after deletion is an effective but not efficient way due to …

Machine UnlearningRepresentation Learning