Get the latest tech news
Design Patterns for Securing LLM Agents Against Prompt Injections
This new paper by 11 authors from organizations including IBM, Invariant Labs, ETH Zurich, Google and Microsoft is an excellent addition to the literature on prompt injection and LLM security. …
This new paper by 11 authors from organizations including IBM, Invariant Labs, ETH Zurich, Google and Microsoft is an excellent addition to the literature on prompt injection and LLM security. Furthermore, their outputs should not pose downstream risks — such as exfiltrating sensitive information (e.g., via embedded links) or manipulating future agent behavior (e.g., harmful responses to a user query). For example, suppose that a malicious user asks a customer service chatbot for a quote on a new car and tries to prompt inject the agent to give a large discount.
Or read this on Hacker News
