OWASP Top 10 for LLMs: A Pentester's Guide to Attacking and Defending
How to not get pwned building with LLMs. A red teamer's take on the new threat landscape.
2 posts with this tag
How to not get pwned building with LLMs. A red teamer's take on the new threat landscape.
I tested 158 attack prompts against an open-source LLM and found a 27% success rate. Here's the methodology.