An Optimal Feature Extraction using Deep Learning Technique for Trojan Detection and Validation using Game Theory

Abstract

In modern electronic design, hardware Trojan has emerged as a major threat in the hardware security. To detect the hardware Trojan is a major problem in testing process because of their inherent concealed nature. In this work, we propose a deep learning-based Trojan classification approach, which extracts the optimal feature to indicate the nets affected by the Trojan module. In this approach, a handcrafted algorithm along with the structural report is also analyzed for extracting further features of the gate level netlist, which stamp out the requirement of golden chip. This detection technique is also validated using game theoretical approach, which is modelled as zero-sum game between the attacker and the defender. The Simulation is employed on ISCAS’85, ISCAS’89 and Trust-HUB circuits and the deep learning algorithm performs the best in detection and classification of Trojan type with an average True positive rate of 96.69% and an accuracy of 96.25%.