Skip to content
InfoResearchPeer-reviewed

A Dual-Purpose Framework for Backdoor Defense and Backdoor Amplification in Diffusion Models

Published
Record updated
View JSON

Summary

PureDiffusion is a dual-purpose framework for diffusion models that inverts backdoor triggers for defense and reinforces them for attack amplification. Its defense uses two novel loss functions based on trigger-induced distribution shifts across timesteps and denoising consistency, followed by a detection method. Reported results include near-perfect detection accuracy and attack success rates of nearly 100% for existing backdoor attacks, with training time reduced by up to 20x.