VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models

Understand

Diffusion Models (DMs) are state-of-the-art generative models that learn a reversible corruption process from iterative noise addition and denoising.

• They are the backbone of many generative AI applications, such as text-to-image conditional generation.
• However, recent studies have shown that basic unconditional DMs (e.g., DDPM and DDIM) are vulnerable to backdoor injection, a type of output manipulation attack triggered by a maliciously embedded pattern at model input.
• This paper presents a unified backdoor attack framework (VillanDiffusion) to expand the current scope of backdoor analysis for DMs.