arXiv Computer Vision By Tuo Chen, Jie Gui, Minjing Dong, Lanting Fang, Ju Jia, Benlei Cui, Jian Liu

DEFUSE: Generalizable Backdoor Defense for Self-Supervised Encoders with Generative Priors

Read the original on arXiv Computer Vision →

DEFUSE is a backdoor detection framework for self‑supervised encoders that uses a conditional diffusion generative model to estimate representation‑conditioned image likelihoods. By fine‑tuning a pretrained diffusion model, DEFUSE performs semantic reconstruction in a reference encoder’s representation space, enabling it to detect backdoors without needing uninfected data or precomputed pseudo‑labels. Experiments show that DEFUSE outperforms existing detectors on both visual SSL and vision‑language encoders, reducing reliance on prior knowledge of the victim model or attack strategy.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

arXiv AI
Jun 11

Diffusion-based Cumulative Adversarial Purification for Vision Language Models

arXiv:2506. 03933v2 Announce Type: replace-cross Abstract: Vision Language Models (VLMs) have shown remarkable capabilities in multimodal understanding, yet their susceptibility to adversarial perturbations poses a significant threat to their reliability in real-world applications.

By Jia Fu, Yongtao Wu, Yihang Chen, Kunyu Peng, Xiao Zhang, Volkan Cevher, Sepideh Pashami, Anders Holst