# New framework for auditing machine unlearning

DevFeed: [New framework for auditing machine unlearning](<https://devfeed.tech/articles/new-framework-for-auditing-machine-unlearning-6839.md>)

Original publisher: [Read original article](<https://research.google/blog/new-framework-for-auditing-machine-unlearning/>)

Published: 2026-06-10T17:34:55Z

Content type: article

Language: en

Sources: [The latest research from Google](<https://devfeed.tech/sources/the-latest-research-from-google.md>)

Topics: [Algorithms & Theory](<https://devfeed.tech/topics/algorithms-theory.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [datasets](<https://devfeed.tech/topics/datasets.md>), [Responsibility & Safety](<https://devfeed.tech/topics/responsibility-safety.md>), [Google](<https://devfeed.tech/topics/google.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [algorithms-theory](<https://devfeed.tech/tags/algorithms-theory.md>), [compliance](<https://devfeed.tech/tags/compliance.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [models](<https://devfeed.tech/tags/models.md>), [research](<https://devfeed.tech/tags/research.md>), [responsible-ai](<https://devfeed.tech/tags/responsible-ai.md>), [safety](<https://devfeed.tech/tags/safety.md>), [security-privacy-and-abuse-prevention](<https://devfeed.tech/tags/security-privacy-and-abuse-prevention.md>), [statistical-significance](<https://devfeed.tech/tags/statistical-significance.md>), [testing](<https://devfeed.tech/tags/testing.md>), [training](<https://devfeed.tech/tags/training.md>)

## AI overview

Google Research introduces Regularized f-Divergence Kernel Tests, a framework for auditing machine unlearning through black-box statistical comparisons of model outputs. The method is designed to improve sensitivity and flexibility while controlling false positives and reducing false negatives as sample sizes grow.

## Source excerpt

Algorithms & Theory