CGCE: Classifier-Guided Concept Erasure in Generative Models

TL;DR

CGCE introduces a scalable, classifier-guided framework for robust concept erasure in generative models, effectively balancing safety and quality without altering original model weights.

Contribution

The paper presents a novel plug-and-play method that enhances concept erasure robustness in generative models using lightweight classifiers on text embeddings.

Findings

Achieves state-of-the-art robustness against adversarial attacks.

Maintains high generative quality on safe prompts.

Applicable to various T2I and T2V models.

Abstract

Recent advancements in large-scale generative models have enabled the creation of high-quality images and videos, but have also raised significant safety concerns regarding the generation of unsafe content. To mitigate this, concept erasure methods have been developed to remove undesirable concepts from pre-trained models. However, existing methods remain vulnerable to adversarial attacks that can regenerate the erased content. Moreover, achieving robust erasure often degrades the model's generative quality for safe, unrelated concepts, creating a difficult trade-off between safety and performance. To address this challenge, we introduce Classifier-Guided Concept Erasure (CGCE), an efficient plug-and-play framework that provides robust concept erasure for diverse generative models without altering their original weights. CGCE uses a lightweight classifier operating on text embeddings to first detect and then refine prompts containing undesired concepts. This approach is highly scalable, allowing for multi-concept erasure by aggregating guidance from several classifiers. By modifying only unsafe embeddings at inference time, our method prevents harmful content generation while preserving the model's original quality on benign prompts. Extensive experiments show that CGCE achieves state-of-the-art robustness against a wide range of red-teaming attacks. Our approach also maintains high generative utility, demonstrating a superior balance between safety and performance. We showcase the versatility of CGCE through its successful application to various modern T2I and T2V models, establishing it as a practical and effective solution for safe generative AI.