GrOCE:Graph-Guided Online Concept Erasure for Text-to-Image Diffusion Models

TL;DR

GrOCE is a training-free, graph-guided framework for precise online removal of target concepts in text-to-image diffusion models, preserving non-target semantics and adapting to evolving concept sets.

Contribution

It introduces a novel, dynamic semantic graph approach for online concept erasure that outperforms existing methods in accuracy and stability without requiring fine-tuning.

Findings

Achieves state-of-the-art results on Concept Similarity and FID metrics.

Effectively removes target concepts while preserving non-target semantics.

Operates efficiently without costly fine-tuning.

Abstract

Concept erasure aims to remove harmful, inappropriate, or copyrighted content from text-to-image diffusion models while preserving non-target semantics. However, existing methods either rely on costly fine-tuning or apply coarse semantic separation, often degrading unrelated concepts and lacking adaptability to evolving concept sets. In this paper, we propose Graph-Guided Online Concept Erasure (GrOCE), a training-free framework that performs precise and context-aware online removal of target concepts. GrOCE constructs dynamic semantic graphs to identify clusters of target concepts and selectively suppress their influence within text prompts. It consists of three synergistic components: (1) dynamic semantic graph construction (Construct) incrementally builds a weighted graph over vocabulary concepts to capture semantic affinities; (2) adaptive cluster identification (Identify) extracts a target concept cluster through multi-hop traversal and diffusion-based scoring to quantify semantic influence; and (3) selective severing (Sever) removes semantic components associated with the target cluster from the text prompt while retaining non-target semantics and the global sentence structure. Extensive experiments demonstrate that GrOCE achieves state-of-the-art performance on the Concept Similarity (CS) and Fr\'echet Inception Distance (FID) metrics, offering efficient, accurate, and stable concept erasure.