pith. sign in

arxiv: 2501.00054 · v1 · pith:VS75WCNPnew · submitted 2024-12-28 · 💻 cs.LG · cs.AI· cs.CL

AdvAnchor: Enhancing Diffusion Model Unlearning with Adversarial Anchors

classification 💻 cs.LG cs.AIcs.CL
keywords anchorsconceptsadvanchoradversarialperformancediffusionfine-tuningmethods
0
0 comments X
read the original abstract

Security concerns surrounding text-to-image diffusion models have driven researchers to unlearn inappropriate concepts through fine-tuning. Recent fine-tuning methods typically align the prediction distributions of unsafe prompts with those of predefined text anchors. However, these techniques exhibit a considerable performance trade-off between eliminating undesirable concepts and preserving other concepts. In this paper, we systematically analyze the impact of diverse text anchors on unlearning performance. Guided by this analysis, we propose AdvAnchor, a novel approach that generates adversarial anchors to alleviate the trade-off issue. These adversarial anchors are crafted to closely resemble the embeddings of undesirable concepts to maintain overall model performance, while selectively excluding defining attributes of these concepts for effective erasure. Extensive experiments demonstrate that AdvAnchor outperforms state-of-the-art methods. Our code is publicly available at https://anonymous.4open.science/r/AdvAnchor.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. CoreUnlearn: Rethinking Concept Unlearning through Disentangled Component-Level Erasure in Text-guided Diffusion Models

    cs.CR 2026-06 unverdicted novelty 4.0

    CoreUnlearn uses a Component Extraction Module and Swap Disentangling Strategy to remove only erasure-critical components from concept embeddings in diffusion models.