Securing AI: From Models to Agents

Por: Honghui Xu's IntelliTrust Lab

AI is rapidly evolving from chatbots to autonomous agents. But as these systems become more capable, they also become more vulnerable.

Hosted by Dr. Honghui Xu and his PhD students, this podcast explores the foundations, attacks, defenses, and future of AI security.

Through research-driven discussions, we break down topics such as prompt injection, indirect attacks, multi-agent security, backdoors, model robustness, and secure AI deployment.

Whether you’re a researcher, engineer, student, or simply curious about the future of AI, this podcast helps you understand how to build and secure the

12 episodios disponibles