research
∙
05/07/2023
Text-to-Image Diffusion Models can be Easily Backdoored through Multimodal Data Poisoning
With the help of conditioning mechanisms, the state-of-the-art diffusion...
share
research
∙
03/03/2023
NCL: Textual Backdoor Defense Using Noise-augmented Contrastive Learning
At present, backdoor attacks attract attention as they do great harm to ...
research
∙
10/20/2022
Apple of Sodom: Hidden Backdoors in Superior Sentence Embeddings via Contrastive Learning
This paper finds that contrastive learning can produce superior sentence...
research
∙
06/03/2022