Skip to content
Google Research·· 2026-06-11AI score38

New framework for auditing machine unlearning

New framework for auditing machine unlearning

AI introduction

At AISTATS 2026, Google Research introduced Regularized f-Divergence Kernel Tests, a framework for auditing machine unlearning with greater sensitivity and flexibility.

A summary is available. Open the original source for the full article. Read source

Source: Google Research · research.google

#论文/研究#安全/对齐#数据/训练#Google