Mist: Towards Improved Adversarial Examples for Diffusion Models

Published in arXiv preprint, 2023

Mist studies the cross-method transferability of adversarial examples for diffusion models and combines complementary objectives to make protective watermarks more robust to common defenses.

Recommended citation: Liang, C.* and Wu, X.* (2023). "Mist: Towards Improved Adversarial Examples for Diffusion Models." arXiv:2305.12683.
Download Paper