ЗащитаОригинал на английском
Your AI red team may be finding the same prompt injection thousands of times
Русский перевод готовится и скоро появится на сайте. Пока доступен оригинал на английском.
AI agents retrained on a bigger pile of prompt injection attacks came out easier to hijack in three of four tests run by researchers at the University of Waterloo, Zhejiang University and KTH Royal Institute of Technology. The automated red-teaming tool that found more working at
Help Net Security··3 мин чтения
AI agents retrained on a bigger pile of prompt injection attacks came out easier to hijack in three of four tests run by researchers at the University of Waterloo, Zhejiang University and KTH Royal Institute of Technology. The automated red-teaming tool that found more working attacks produced the weaker defense. Prompt injection purple-teaming workflow (Source: Research paper) Someone hides instructions in an email, a web page or a tool’s output, and the AI agent that … More → The post Your AI red team may be finding the same prompt injection thousands of times appeared first on Help Net Security.