2023-05-18, 09:15–09:45, Ville-Marie
In this talk, I will provide a high-level overview of the fundamentals of large language models, with a focus on GPT models. My goal is to share insights from a security research perspective and inspire researchers to explore the potential of GPT models in their own labs. Specifically, I will cover topics such as semantic searching, few-shot learning, and code generation and provide basic examples and experiments to illustrate these concepts. Whether you're new to GPT models or have experience working with them, this talk aims to provide a fresh perspective on how they can be leveraged to empower security teams and spark new ideas for research.
Roberto Rodriquez is a Principal Security Researcher at the Microsoft Security Research organization. He is the founder of the Open Threat Research (OTR) community and author of several open-source projects, such as the Threat Hunter Playbook, OSSEM, SimuLand, ATT&CK Python Client, Security Datasets, and more. You can find all his contributions to the InfoSec community in the open OTR GitHub repository and can follow him in Twitter @Cyb3rWard0g.