Search Results for author:
Found 2 papers, 0 papers with code
Probing Unlearned Diffusion Models: A Transferable Adversarial Attack Perspective
Specifically, we employ an adversarial search strategy to search for the adversarial embedding which can transfer across different unlearned models.
Is It Possible to Backdoor Face Forgery Detection with Natural Triggers?
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.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
