Democratizing AI in Low-Resource Settings: Towards Efficient, Reliable, and Self-Improving Knowledge Adaptation
 

Abstract

Hardware is at the heart of computing systems. However, in recent years, there have been more attacks exploiting hardware vulnerabilities and other exploits that even traditional software-based protections cannot prevent. Hardware fuzzing has shown promise in detecting vulnerabilities in large-scale designs, such as modern processors. In this talk, PhD candidate from Texas A&M University Chen Chen will first introduce hardware fuzzing as a method for finding vulnerabilities and outline its three major problems. He will then detail how fuzzing techniques can be combined with traditional methods, such as formal verification and information flow tracking, to address these problems. Finally, he will discuss AI for hardware fuzzing and future research directions.
 

Biography

Chen Chen is a PhD candidate in the Department of Electrical and Computer Engineering at Texas A&M University, advised by JV Rajendran. He received his BS degree from Purdue University. His research focuses on hardware security, with publications in top-tier conferences, including USENIX Security, NDSS, DAC, ICCAD, and DATE. He received the Distinguished Paper Award at USENIX Security 2024. He co-organizes HackTheSilicon, the world's largest hardware security capture-the-flag competition, co-located with DAC, USENIX Security, CHES, and DATE. He also founded and led the first Texas A&M Cohort for Hardware Security. In addition, he serves on the program committee of the CWE RTL Ad-Hoc Working Group.