GrOCE:Graph-Guided Online Concept Erasure for Text-to-Image Diffusion Models
This addresses the need for efficient and precise concept erasure in text-to-image models, which is crucial for safety and copyright compliance, though it is an incremental improvement over existing methods.
The paper tackles the problem of removing harmful or copyrighted content from text-to-image diffusion models without degrading unrelated concepts, proposing GrOCE, a training-free framework that achieves state-of-the-art performance on Concept Similarity and Fréchet Inception Distance metrics.
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. To alleviate this issue, we propose Graph-Guided Online Concept Erasure (GrOCE), a training-free framework that performs precise and adaptive concept removal through graph-based semantic reasoning. GrOCE models concepts and their interrelations as a dynamic semantic graph, enabling principled reasoning over dependencies and fine-grained isolation of undesired content. It comprises three components: (1) Dynamic Topological Graph Construction for incremental graph building, (2) Adaptive Cluster Identification for multi-hop traversal with similarity-decay scoring, and (3) Selective Edge Severing for targeted edge removal while preserving global semantics. Extensive experiments demonstrate that GrOCE achieves state-of-the-art performance on Concept Similarity (CS) and Fréchet Inception Distance (FID) metrics, offering efficient, accurate, and stable concept erasure without retraining.