Using Path Features for Hardware Trojan Detection Based on Machine Learning Techniques

As the outsourcing process in the design and fabrication to third parties becomes more popular in the IC industry, the consciousness of hardware security has been rising these years. In this paper, we propose a novel method for hardware Trojan detection using specific path features at the gate level. In the training flow, path classifiers can be trained with SVM and RF algorithms using the path features from the trained circuits. In the classifying flow, an average of 0.96 on the F1-score in the results of the path classification demonstrates that logical paths can be easily classified into Trojan paths and Trojan-free paths with the trained path classifiers. In the localizing flow, the intersections between the logical paths can be favorable for precisely localizing the Trojan gates. As the FPRs are kept low to prevent normal gates from misclassifying into the Trojan gates, the high TPRs can be obtained for localizing the Trojan gates with the proposed scoring method.