Hardware Trojan detection with linear regression based gate-level characterization

Due to outsourcing of IC fabrication, chip supply contamination is a clear and present danger, of which hardware Trojans (HTs) pose the greatest threat. This paper reviews the limitation of existing gate level characterization approaches to HT detection and presents a new detection method with a faster estimation of gate scaling factors by solving the normal equation of linear regression model. The HT-infected circuit can be distinguished from the genuine circuit without the need for a golden reference chip by their discrepancies in the bias parameter of the linear regression and a subset of the accurately estimated scaling factors. It has high detection sensitivity as long as the Trojan-to-circuit gate count ratio exceeds 0.4%.