Automating Evaluation of Diffusion Model Unlearning with (Vision-) Language Model World Knowledge

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yeats, Eric, Hannan, Darryl, Kvinge, Henry, Doster, Timothy, Mahan, Scott
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911049135947776
author Yeats, Eric
Hannan, Darryl
Kvinge, Henry
Doster, Timothy
Mahan, Scott
author_facet Yeats, Eric
Hannan, Darryl
Kvinge, Henry
Doster, Timothy
Mahan, Scott
contents Machine unlearning (MU) is a promising cost-effective method to cleanse undesired information (generated concepts, biases, or patterns) from foundational diffusion models. While MU is orders of magnitude less costly than retraining a diffusion model without the undesired information, it can be challenging and labor-intensive to prove that the information has been fully removed from the model. Moreover, MU can damage diffusion model performance on surrounding concepts that one would like to retain, making it unclear if the diffusion model is still fit for deployment. We introduce autoeval-dmun, an automated tool which leverages (vision-) language models to thoroughly assess unlearning in diffusion models. Given a target concept, autoeval-dmun extracts structured, relevant world knowledge from the language model to identify nearby concepts which are likely damaged by unlearning and to circumvent unlearning with adversarial prompts. We use our automated tool to evaluate popular diffusion model unlearning methods, revealing that language models (1) impose semantic orderings of nearby concepts which correlate well with unlearning damage and (2) effectively circumvent unlearning with synthetic adversarial prompts.
format Preprint
id arxiv_https___arxiv_org_abs_2507_07137
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Automating Evaluation of Diffusion Model Unlearning with (Vision-) Language Model World Knowledge
Yeats, Eric
Hannan, Darryl
Kvinge, Henry
Doster, Timothy
Mahan, Scott
Machine Learning
Computation and Language
Machine unlearning (MU) is a promising cost-effective method to cleanse undesired information (generated concepts, biases, or patterns) from foundational diffusion models. While MU is orders of magnitude less costly than retraining a diffusion model without the undesired information, it can be challenging and labor-intensive to prove that the information has been fully removed from the model. Moreover, MU can damage diffusion model performance on surrounding concepts that one would like to retain, making it unclear if the diffusion model is still fit for deployment. We introduce autoeval-dmun, an automated tool which leverages (vision-) language models to thoroughly assess unlearning in diffusion models. Given a target concept, autoeval-dmun extracts structured, relevant world knowledge from the language model to identify nearby concepts which are likely damaged by unlearning and to circumvent unlearning with adversarial prompts. We use our automated tool to evaluate popular diffusion model unlearning methods, revealing that language models (1) impose semantic orderings of nearby concepts which correlate well with unlearning damage and (2) effectively circumvent unlearning with synthetic adversarial prompts.
title Automating Evaluation of Diffusion Model Unlearning with (Vision-) Language Model World Knowledge
topic Machine Learning
Computation and Language
url https://arxiv.org/abs/2507.07137