🔗 Security Engineering Blog

How NOT to Train Your Hack Bot: Dos and Don'ts of Building Offensive GPTs

2024-02-06 17:52:12 UTC

Learn the Dos and Don'ts of building offensive language models (LLMs) in the hunt for security vulnerabilities in applications. In an upcoming talk, experts Shane Caldwell and Ariel Herbert-Voss will delve into the potential and limitations of using LLMs like GPT4 for offensive security operations. This session will explore the inner workings of LLMs and reveal cutting-edge techniques to leverage them in offensive contexts. For more information and presentation materials, visit the provided link.

Read More