ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2402.19150
16
5

Unveiling Typographic Deceptions: Insights of the Typographic Vulnerability in Large Vision-Language Model

29 February 2024
Hao-Ran Cheng
Erjia Xiao
Jindong Gu
Le Yang
Jinhao Duan
Jize Zhang
Jiahang Cao
Kaidi Xu
Renjing Xu
ArXivPDFHTML
Abstract

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%42.07\%42.07% to 13.90%13.90\%13.90% when LVLMs confront typographic attacks.

View on arXiv
Comments on this paper