Salient Conditional Diffusion for Defending Against Backdoor Attacks. (arXiv:2301.13862v1 [cs.LG])

We propose a novel algorithm, Salient Conditional Diffusion (Sancdifi), a
state-of-the-art defense against backdoor attacks. Sancdifi uses a denoising
diffusion probabilistic model (DDPM) to degrade an image with noise and then
recover said image using the learned reverse diffusion. Critically, we compute
saliency map-based masks to condition our diffusion, allowing for stronger
diffusion on the most salient pixels by the DDPM. As a result, Sancdifi is
highly effective at diffusing out triggers in data poisoned by backdoor
attacks. At the …

algorithm art attacks backdoor backdoor attacks compute defense map masks noise novel recover result reverse state