1 code implementation • 30 Apr 2024 • Xiaoxuan Han, Songlin Yang, Wei Wang, Yang Li, Jing Dong
Specifically, we employ an adversarial search strategy to search for the adversarial embedding which can transfer across different unlearned models.
no code implementations • 31 Dec 2023 • Xiaoxuan Han, Songlin Yang, Wei Wang, Ziwen He, Jing Dong
To further investigate natural triggers, we propose a novel analysis-by-synthesis backdoor attack against face forgery detection models, which embeds natural triggers in the latent space.