Choose Your Anchor Wisely: Effective Unlearning Diffusion Models via Concept Reconditioning
Keywords: Machine Unlearning, Diffusion Models.
TL;DR: We introduce COncept REconditioning (CORE), a simple yet effective approach for unlearning in diffusion models.
Abstract: Large-scale conditional diffusion models (DMs) have demonstrated exceptional ability in generating high-quality images from textual descriptions, gaining widespread use across various domains. However, these models also carry the risk of producing harmful, sensitive, or copyrighted content, creating a pressing need to remove such information from their generation capabilities. While retraining from scratch is prohibitively expensive, machine unlearning provides a more efficient solution by selectively removing undesirable knowledge while preserving utility. In this paper, we introduce \textbf{COncept REconditioning (CORE)}, a simple yet effective approach for unlearning diffusion models. Similar to some existing approaches, CORE guides the noise predictor conditioned on forget concepts towards an anchor generated from alternative concepts. However, CORE introduces key differences in the choice of anchor and retain loss, which contribute to its enhanced performance. We evaluate the unlearning effectiveness and retainability of CORE on UnlearnCanvas. Extensive experiments demonstrate that CORE surpasses state-of-the-art methods including its close variants and achieves near-perfect performance, especially when we aim to forget multiple concepts. More ablation studies show that CORE's careful selection of the anchor and retain loss is critical to its superior performance.
Primary Area: alignment, fairness, safety, privacy, and societal considerations
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 9536
Loading