3 papers
cs.CV2025
Improving Generalizability and Undetectability for Targeted Adversarial Attacks on Multimodal Pre-trained Models
Zhifang Zhang, Jiahan Zhang, Shengjie Zhou +4
Multimodal pre-trained models (e.g., ImageBind), which align distinct data modalities into a shared embedding space, have shown remarkable success across downstream tasks. However,…
cs.LG2024
Candidate Pseudolabel Learning: Enhancing Vision-Language Models by Prompt Tuning with Unlabeled Data
Jiahan Zhang, Qi Wei, Feng Liu +1
Fine-tuning vision-language models (VLMs) with abundant unlabeled data recently has attracted increasing attention. Existing methods that resort to the pseudolabeling strategy woul…
cs.CV2024
Test-Time Multimodal Backdoor Detection by Contrastive Prompting
Yuwei Niu, Shuo He, Qi Wei +3
While multimodal contrastive learning methods (e.g., CLIP) can achieve impressive zero-shot classification performance, recent research has revealed that these methods are vulnerab…