UFID: A Unified Framework for Input-level Backdoor Detection on Diffusion Models

arXiv:2404.01101v1 Announce Type: cross
Abstract: Diffusion Models are vulnerable to backdoor attacks, where malicious attackers inject backdoors by poisoning some parts of the training samples during the training stage. This poses a serious threat to the downstream users, who query the diffusion models through the API or directly download them from the internet. To mitigate the threat of backdoor attacks, there have been a plethora of investigations on backdoor detections. However, none of them designed a specialized backdoor detection method …

arxiv backdoor cs.cr cs.cv cs.lg detection diffusion diffusion models framework type