Skip to content
InfoResearchPeer-reviewed

Forgotten Horizons in Concept Erasure: Safeguarding Close-Proximity Concepts in Text-to-Image Models

Published
Record updated
View JSON

Summary

Researchers propose SCPC, a framework for concept erasure in text-to-image models that removes a target concept while preserving semantically close concepts. Existing methods often degrade close-proximity concepts; for example, erasing 'English Springer' may hurt generation of 'Cocker Spaniel'. SCPC samples semantic-agnostic embeddings within a hypersphere around the erased concept, refines sampling with a learnable adversarial offset, and applies a semantic-agnostic knowledge distillation objective. Experiments reportedly show it erases targets while preserving generation quality for both close and distant concepts. Code and data are promised for future release.