Towards Developing Secure and Trustworthy Hardware: A Perspective on Securing Semiconductor Supply Chain

ABSTRACT

Hardware is the backbone of modern computing systems. Unlike software, which can be patched to fix bugs or vulnerabilities, compromised chips cannot be patched once fabricated. Recent attacks and case studies show that compromised hardware can jeopardize the security and integrity of digital infrastructure, from national security risks to reputational damage for chip design companies. This highlights an urgent need to critically examine existing approaches and rethink how we develop secure and trustworthy hardware, especially as the threat landscape evolves with increasingly sophisticated adversaries. This talk will provide an overview of my efforts pertaining to reinforcement learning and explainable graph neural networks to develop secure and trustworthy hardware from the perspective of securing the globalized semiconductor supply chain.

BIOGRAPHY

Satwik Patnaik is an Assistant Professor in the Department of Electrical and Computer Engineering at the University of Delaware, Newark, DE, USA. He was a postdoctoral researcher with the Department of Electrical and Computer Engineering at Texas A&M University and received his Ph.D. in Electrical Engineering from Tandon School of Engineering, New York University.

His research interests lie at the intersection of VLSI design, hardware security computer-aided design, and machine learning. The outcomes of this research have led to 1 book and 52 peer-reviewed publications in top-tier conferences and journals in computer security and electronic design automation. During his Ph.D., he received the Bronze Medal in the Graduate Category at the ACM/SIGDA Student Research Competition held at ICCAD 2018, the Best Paper Award at the Applied Research Competition (ARC) held in conjunction with Cyber Security Awareness Week (CSAW) in 2017, and the third place at the ARC competition in 2021. In addition, he has co-organized 2 global hardware security competitions (HeLLO-CTF 2021 and AI vs. Humans 2022) and served as the security track chair for ACM CADAthlon, co-located with ICCAD 2022 and ICCAD 2023. He is actively engaged as a TPC member in leading CAD conferences and is an active reviewer for several journals