RVAsec 2025 Video: Morgan Stuart
Data Scientist and Engineer – Canopy Nine, LLC
Title: Large Language Models for Hackers
Wield your own AI agents, for fun and profit, with open-weight Large Language Models. In this talk, the audience will learn the foundational data science that empowers LLMs to help…and hallucinate, before diving into a tutorial on “agentic” LLM techniques. Along the way, key concepts and methods are related to NIST’s AI Risk Management Framework (NIST AI 600-1) and their adversarial machine learning taxonomy (NIST AI 100-2e2023). Cut through the hype – see the limitations and attack surfaces for yourself, and explore ways you could incorporate these tools into your own practice.