Roman Yampolskiy

AI safety and security researcher, author of "AI: Unexplainable, Unpredictable, Uncontrollable", professor in cybersecurity, founder of the Cyber Security Lab focusing on AI safety and ethics, speaker on AI risk and alignment topics.

About

Roman Yampolskiy is a leading expert in AI safety and security research.
He is a professor and founder of the Cyber Security Lab, with a focus on protecting society from AI risks.
Yampolskiy authored the book "AI: Unexplainable, Unpredictable, Uncontrollable," addressing critical issues in AI behavior and control.
He is recognized for his work on AI alignment, malicious AI prevention, and AI ethics.
His contributions include academic publications, keynote talks, and advancing frameworks for responsible AI development.