Hacker Newsnew | past | comments | ask | show | jobs | submitlogin
System prompt exposure: how AI image generators may leak sensitive instructions (invicti.com)
1 point by harisec on Nov 12, 2024 | hide | past | favorite | 1 comment


Recraft’s image generation service could leak its internal system prompts due to its unique architecture combining Claude (an AI language model) with a diffusion model. Unlike other image generators, Recraft could perform calculations and answer questions, which led to the discovery that carefully crafted prompts could expose the system’s internal instructions.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: