AI Security · 18. September 2024
In this post, I introduce the PALIM framework that I have developed to build secure GenAI applications on top of existing LLMs. It consists of five components to understand and look for in your planned applications design. For each component assume the worst case and then evaluate the impact.
27. December 2018
This is the standard questions you usually hear from system designers or developers: "What could possibly go wrong? We thought about everything." Well, experience shows, no they don't.