11:30
-
13:30
May 08, 2024
Join us for an LLM security demo with real-world examples and engage in a trivia game centered around it!
LLM security involves measures and techniques used to ensure the safety, privacy, and integrity of large language models like OpenAI's GPT models. We start with some attacks and stats on LLM security, followed by a demo of LLM API test cases with examples from past incidents. You will then have to answer 5-10 multiple choice/answer questions based on what you learned in the demo. Winners will get swags for each answer they get right!