Automatic Feature Selection of Hardware Layout: A Step toward Robust Hardware Trojan Detection

Recently, the problem of hardware Trojan detection has gained a tangible significance in academia and industry. That problem, by its nature, is complex, time consuming and error prone due to design and fabrication outsourcing of hardware circuits to external untrusted foundries. Researchers have proposed different approaches, either destructive or non-destructive, to overcome that problem. The destructive approach depends on reverse engineering via decapsulation, delayering and layout identification. This paper presents a first trial of a new approach that can afford an automatic and robust solution for the step of layout identification. The proposed technique takes the underlying digital circuit as input, and automatically determines its basic features using Haar feature extractor. Based on that features, a decision tree is trained to act as a weak classifier, which is later boosted, by making use of AdaBoost learning algorithm, to produce a strong classifier in a chain of cascaded classifiers. Accordingly, a classification model is built up to provide an automatic hardware Trojan location and detection tool. To evaluate the proposed model, ISCAS89 benchmark dataset was used for training and testing. The hardware dataset has been altered deliberately to show different Trojan examples –namely, Trojan insertion, Trojan deletion and Trojan parametric- inside hardware circuits. By investigating the underlying experimental results, the capabilities of the proposed model are evaluated, and the evaluation shows that the approach can detect different hardware Trojan types in different circuit layouts, with high accuracy rate. The proposed approach is not only automatic, but also robust and promising.