Unveiling Typographic Deceptions: Insights Of The Typographic Vulnerability In Large Vision-language Model

Cheng Hao, Xiao Erjia, Gu Jindong, Yang Le, Duan Jinhao, Zhang Jize, Cao Jiahang, Xu Kaidi, Xu Renjing. Arxiv 2024

[Paper]    
Multimodal Models Pretraining Methods Security Training Techniques

Large Vision-Language Models (LVLMs) rely on vision encoders and Large Language Models (LLMs) to exhibit remarkable capabilities on various multi-modal tasks in the joint space of vision and language. However, the Typographic Attack, which disrupts vision-language models (VLMs) such as Contrastive Language-Image Pretraining (CLIP), has also been expected to be a security threat to LVLMs. Firstly, we verify typographic attacks on current well-known commercial and open-source LVLMs and uncover the widespread existence of this threat. Secondly, to better assess this vulnerability, we propose the most comprehensive and largest-scale Typographic Dataset to date. The Typographic Dataset not only considers the evaluation of typographic attacks under various multi-modal tasks but also evaluates the effects of typographic attacks, influenced by texts generated with diverse factors. Based on the evaluation results, we investigate the causes why typographic attacks may impact VLMs and LVLMs, leading to three highly insightful discoveries. By the examination of our discoveries and experimental validation in the Typographic Dataset, we reduce the performance degradation from \(42.07%\) to \(13.90%\) when LVLMs confront typographic attacks.

Similar Work