Secure By Dezign
Invisible Commands: Visual Prompt Injection Against Multimodal LLMs
March 12 · 10 min · Season 1 · Episode 36 · 4.4 MB
0:00-10:32
Streams straight from the publisher. podnod never proxies or re-hosts episode audio.
When your image is the attack vector, every picture becomes a potential payload. Technical walkthrough of visual prompt injection against multimodal LLMs including GPT-4V and Gemini Vision.
No links were found in this episode’s notes.