5 citations · 5 across the 2 of their papers we have counts for
5 papers · 1 filter
Fighting Fire with Fire (F3): A Training-free and Efficient Visual Adversarial Example Purification Method in LVLMs
Yudong Zhang, Ruobing Xie, Yiqing Huang +5
Recent advances in large vision-language models (LVLMs) have showcased their remarkable capabilities across a wide range of multimodal vision-language tasks. However, these models…
QAVA: Query-Agnostic Visual Attack to Large Vision-Language Models
Yudong Zhang, Ruobing Xie, Jiansheng Chen +3
In typical multimodal tasks, such as Visual Question Answering (VQA), adversarial attacks targeting a specific image and question can lead large vision-language models (LVLMs) to p…
Enhancing Contrastive Learning Inspired by the Philosophy of "The Blind Men and the Elephant"
Yudong Zhang, Ruobing Xie, Jiansheng Chen +3
Contrastive learning is a prevalent technique in self-supervised vision representation learning, typically generating positive pairs by applying two data augmentations to the same…
DHCP: Detecting Hallucinations by Cross-modal Attention Pattern in Large Vision-Language Models
Yudong Zhang, Ruobing Xie, Xingwu Sun +5
Large vision-language models (LVLMs) have demonstrated exceptional performance on complex multimodal tasks. However, they continue to suffer from significant hallucination issues,…
PIP: Detecting Adversarial Examples in Large Vision-Language Models via Attention Patterns of Irrelevant Probe Questions
Yudong Zhang, Ruobing Xie, Jiansheng Chen +2
Large Vision-Language Models (LVLMs) have demonstrated their powerful multimodal capabilities. However, they also face serious safety problems, as adversaries can induce robustness…