Co-occurring associated retained concepts in Diffusion Unlearning

2026-06-23

AI Summary

Diffusion models often inadvertently erase benign concepts that co-occur with harmful content during unlearning—for example, suppressing the concept of “people” when removing nude images—thereby degrading generative capabilities. This work proposes ReCARE, a framework that formally defines and quantifies such co-occurring and retainable entities (CARE). ReCARE automatically constructs a CARE lexicon and introduces a constrained fine-tuning strategy during targeted unlearning to explicitly preserve these essential concepts. We also introduce the CARE score as a dedicated evaluation metric. Experiments across diverse targets—including nudity, Van Gogh style, and tilapia—demonstrate that ReCARE significantly outperforms existing methods in terms of harmful concept removal efficacy, model generalization, and preservation of CARE concepts.

Abstract

Unlearning has emerged as a key technique to mitigate harmful content generation in diffusion models. However, existing methods often remove not only the target concept, but also benign co-occurring concepts. As illustrated in Fig.1, unlearning nudity can unintentionally suppress the concept of person, preventing a model from generating images with person. We define these undesirably suppressed co-occurring concepts that must be preserved CARE (Co-occurring Associated REtained concepts). Then, we introduce the CARE score, a general metric that directly quantifies their preservation across unlearning tasks. With this foundation, we propose ReCARE (Robust erasure for CARE), a framework that explicitly safeguards CARE while erasing only the target concept. ReCARE automatically constructs the CARE-set, a curated vocabulary of benign co-occurring tokens extracted from target images, and leverages this vocabulary during training for stable unlearning. Extensive experiments across various target concepts (Nudity, Van Gogh style, and Tench object) demonstrate that ReCARE achieves overall state-of-the-art performance in balancing robust concept erasure, overall utility, and CARE preservation.

Problem

• Diffusion Unlearning
• Co-occurring Concepts
• Concept Preservation
• Harmful Content Mitigation
• CARE

Innovation

• diffusion unlearning
• CARE
• concept preservation
• ReCARE
• co-occurring concepts