Mitigating Sexual Content Generation via Embedding Distortion in Text-conditioned Diffusion Models

Understand

Diffusion models show remarkable image generation performance following text prompts, but risk generating sexual contents.

• Existing approaches, such as prompt filtering, concept removal, and even sexual contents mitigation methods, struggle to defend against adversarial attacks while maintaining benign image quality.
• In this paper, we propose a novel approach called Distorting Embedding Space (DES), a text encoder-based defense mechanism that effectively tackles these issues through innovative embedding space control.
• DES transforms unsafe embeddings, extracted from a text encoder using unsafe prompts, toward carefully calculated safe embedding regions to prevent unsafe contents generation, while reproducing the original safe embeddings.