Hamed Hassani

Papers

Total Citations

H-Index

About

Hamed Hassani is a leading researcher at the intersection of artificial intelligence, robotics, and safety-critical machine learning. His work primarily focuses on ensuring the secure and reliable deployment of large language models (LLMs) in physical systems, addressing the profound challenges that arise when AI agents interact with humans and the real world. Hassani’s most impactful contributions include pioneering research on the vulnerabilities of LLM-controlled robots, where he has systematically identified and categorized "jailbreaking" attacks that can cause robots to produce harmful behaviors. This work, which has garnered significant attention with over 12 citations across its iterations, is foundational to the emerging field of robotic safety. He has also made critical advances in safe learning under uncertain objectives and constraints, developing non-convex optimization frameworks for domains like robotics and manufacturing. His research on learning dynamics between interacting AI agents further demonstrates his commitment to understanding complex multi-agent systems. Through his development of safety guardrails and his rigorous analysis of adversarial threats, Hassani is shaping the future of trustworthy autonomous systems.