Efficient Machine Learning Model for Hardware Trojan Detection on Register Transfer Level

Abstract

There are many proposed hardware trojan detection techniques developed using Machine Learning (ML) approach. These approaches are carried out in the mainstream area on the gate-level netlist. Meanwhile, the same trojan injection may also be carried out at the Register Transfer Level (RTL). One solution at the RTL level was proposed by Choo et al. They designed ML detection technique using four branching circuit features. These techniques were performed using some models: decision tree, logistic regression, SVM, and k-nearest neighbor with an average True Positive Rate (TPR) of 93.72%. The dataset used in that training model was an artificial one created using the Adaptive Synthetic Sampling (ADASYN) algorithm which inputs are from AES Trust-Hub benchmark. As a result, the data does not fully represent the original benchmark. Also, the extraction of four features is a complex and inefficient process. In this paper, a Trojan detection model is proposed using the original AES, RS232, and wb-conmax dataset which implements a single branch feature called R <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">bit</inf> , which is faster and easier to extract. The results show a competitive accuracy of 92% using just the R <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">bit</inf> feature. The accuracy shows the possibility to build a Trojan detection model which is efficient and accurate.