Empirical Analysis of Goal Hijacking in Large Vision-Language Models via Visual Prompt Injection
Abstract In this study, we explore visual prompt injection (VPI), a method that exploits the ability of large vision-language models (LVLMs) to follow instructions embedded within input images. LVLMs, such as GPT-4V, are designed to interpret and respond to visual prompts. Although this capability enables valuable appl...
Subaru Kimura, Ryota Tanaka, Shumpei Miyawaki et al.
· New Generation Computing · 0 citations