2025-06-21 –, Track 2 (Moody Rm. 101)
In this talk, we’ll explore real-world attack scenarios, recent security incidents, and live demonstrations to show how LLM-based systems are being abused.
Attendees will gain practical insights on exploitation techniques, the latest adversarial AI tactics, and defensive strategies that can be implemented to secure LLM applications.
Large Language Models (LLMs) are revolutionizing industries, but they also introduce a new and rapidly evolving attack surface. The OWASP Top 10 for LLM Applications (2025) highlights the most pressing security vulnerabilities that organizations face today. From Prompt Injection to System Prompt Leakage, Data Poisoning, and Excessive Agency, these vulnerabilities are actively exploited by threat actors in ways that many security teams are unprepared for.
This talk will be interactive, example-driven, and packed with visuals, ensuring that every attendee walks away with a clear understanding of LLM threats and actionable steps to defend against them.
With over 24 years of hands-on experience in information security and IT, specializing in developing security programs with a focus on risk management, I've consistently delivered value for Fortune 100 and 500 companies, as well as the public sector. As the former CISO at Portland Community College, I orchestrated the alignment of security initiatives with the organization's mission and objectives.