4 papers
Detecting Chain-of-Thought Hijacking in Backdoored Multimodal Large Reasoning Models
Zhifang Zhang, Qi Wei, Weitong Chen +5
Chain-of-thought (CoT) reasoning enables multimodal large reasoning models (MLRMs) to solve complex visual problems, but also exposes them to CoT hijacking: an adversary implants a…
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,…
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…
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…