Saved in:
Bibliographic Details
Main Authors: Zhang, Tong, Zhang, Ru, Liu, Jianyi, Yang, Zhen, Liu, Gongshen
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.16342
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Existing concept erasure methods for text-to-image diffusion models commonly rely on fixed anchor strategies, which often lead to critical issues such as concept re-emergence and erosion. To address this, we conduct causal tracing to reveal the inherent sensitivity of erasure to anchor selection and define Sibling Exclusive Concepts as a superior class of anchors. Based on this insight, we propose \textbf{SELECT} (Sibling-Exclusive Evaluation for Contextual Targeting), a dynamic anchor selection framework designed to overcome the limitations of fixed anchors. Our framework introduces a novel two-stage evaluation mechanism that automatically discovers optimal anchors for precise erasure while identifying critical boundary anchors to preserve related concepts. Extensive evaluations demonstrate that SELECT, as a universal anchor solution, not only efficiently adapts to multiple erasure frameworks but also consistently outperforms existing baselines across key performance metrics, averaging only 4 seconds for anchor mining of a single concept.