from Hacker News

System prompt exposure: how AI image generators may leak sensitive instructions

by harisec on 11/12/24, 1:03 PM with 1 comments

  • by harisec on 11/12/24, 1:03 PM

    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.