视觉-大语言模型会被自身生成的排版攻击欺骗
Vision-LLMs Can Fool Themselves with Self-Generated Typographic Attacks
AI总结：
针对视觉-语言模型（LVLM）易受排版攻击却研究不足的问题，提出两种自生成攻击策略，通过模型自身生成误导性文本显著降低其分类性能，为LVLM的安全应用提供实验与方法参考。
摘要：
排版攻击通过向图像添加误导性文本可欺骗视觉-语言模型（LVLM）。近期大型LVLM（如GPT4-V）对此类攻击的易感性研究不足，引发个人助理应用中错误信息加剧的担忧。以往攻击采用随机误导词等简单策略，未充分利用LVLM的语言推理能力。我们引入LVLM排版攻击测试实验设置，提出两种新型自生成攻击：（1）基于类别的攻击，模型识别相似类别欺骗自身；（2）推理型攻击，由先进LVLM生成结合欺骗类别与描述的攻击。实验显示这些攻击使分类性能显著下降高达60%，且在InstructBLIP和MiniGPT4等不同模型上均有效。代码：https://github.com/mqraitem/Self-Gen-Typo-Attack
英文摘要：
Typographic attacks, adding misleading text to images, can deceive vision-language models (LVLMs). The susceptibility of recent large LVLMs like GPT4-V to such attacks is understudied, raising concerns about amplified misinformation in personal assistant applications. Previous attacks use simple strategies, such as random misleading words, which don't fully exploit LVLMs' language reasoning abilities. We introduce an experimental setup for testing typographic attacks on LVLMs and propose two novel self-generated attacks: (1) Class-based attacks, where the model identifies a similar class to deceive itself, and (2) Reasoned attacks, where an advanced LVLM suggests an attack combining a deceiving class and description. Our experiments show these attacks significantly reduce classification performance by up to 60\% and are effective across different models, including InstructBLIP and MiniGPT4. Code: https://github.com/mqraitem/Self-Gen-Typo-Attack
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
