SEC536: Adversarial AI - Penetration Testing AI Systems


Experience SANS training through course previews.
Learn MoreLet us help.
Contact usBecome a member for instant access to our free resources.
Sign UpWe're here to help.
Contact Us
ChatGPT was launched by OpenAI in November 2022. Since then, it has been the subject of many discussions. ChatGPT itself is one application that was built on top of OpenAI’s GPT-3 models. We can programmatically interact with these models via OpenAI API. In this talk, we will go beyond ChatGPT and discuss OpenAI API, fine-tuning our own models for specific tasks, and building security applications on top of them. We will be building a sample application that interprets human requests and performs the basic tasks requested.


Ahmed AbuGharbia, SANS Instructor and SEC545 author, helps practitioners secure generative AI systems by identifying risks, understanding model behavior, and applying practical security controls.
Read more about Ahmed AbuGharbia