Preprint
Aug 2026
DEFUSE: Generalizable Backdoor Defense for Self-Supervised Encoders with Generative Priors
Inspired by Bayesian posterior inference, this work reformulate backdoor detection as a representation-conditioned image likelihood estimation problem parameterized by a conditional diffusion generative model, and fine-tune a pretrained diffusion model, leveraging its generative prior to map data onto the natural image manifold while preserving semantic content.
Tuo Chen, Jie Gui, Minjing Dong et al.
· 0 citations