Hybrid multi‐level hardware Trojan detection platform for gate‐level netlists based on XGBoost

Abstract

Coping with the problem of malicious third-party vendors implanting Hardware Trojan (HT) in the circuit design stage, this paper proposes a hybrid-mode gate-level hardware Trojan detection platform based on the XGBoost algorithm. This detection platform is composed of multi-level HT localization and circuit structure based HT detection. Each wire of the circuit is regarded as a node in multi-level HT localization, and static characteristics of nodes are analysed, combining with dynamic detection to locate HT. The network structure features of the circuit are extracted in modular HT structure detection, aiming to identify HT accurately and rapidly. The hybrid-mode HT detection platform can efficiently meet various detection requirements, such as HT localization or rapid and accurate HT detection. The experiment results on Trust-Hub benchmark show that the multi-level localization can achieve 94.0% location accuracy, and the modular HT structure detection accuracy can achieve 100%. The modular HT structure detection is about four times as fast as the multi-level HT localization on feature extraction. Therefore, multi-level localization and modular HT structure detection can be respectively or cooperatively applied for specific HT detection issues, which proves that the proposed hybrid-mode gate-level HT detection scheme is practical and effective.

Hardware-Trojan Detection at Gate-Level Netlists Using a Gradient Boosting Decision Tree Model and Its Extension Using Trojan Probability Propagation

“…There have been several XGBoost-based HT detection methods proposed [16]- [18]. We compare and evaluate our proposed method with these methods.…”

“…We compare and evaluate our proposed method with these methods. Table 9 shows the results of the proposed method and those in [16]- [18] for comparison. Note that, some of the metrics are not available in the original references, and then they were derived using the other metrics and summarized in Table 9.…”

“…5.1, many machine learning hyperparameters cannot affect model performance very much. For example, an XGBoost-based HT detection method [18] trains the model with its own hyperparameters including eta, max_depth, and min_child_weight. Further, in [19], [20], the XGBoost models are tuned under the hyperparameters of gamma, subsample, and colsam-ple_bytree, though their target does not HT detection.…”

Data Augmented Hardware Trojan Detection Using Label Spreading Algorithm Based Transductive Learning for Edge Computing-Assisted IoT Devices

“…It aims to generate a similarity function based HTD, but the results were not comparable with reported results. An effort to combine static and dynamic features had been attempted in [47] and [48]. Though it had produced 95% average TPR in Trojan detection, the method had not been generalized on varying Trojan circuits.…”

Multi-class identification of urban bus bunching rate based on XGBoost

“…XGBoost model is an improvement on the boosting algorithm, and is currently one of the most mainstream machine learning algorithms. This model has been widely used in medical [8] , information technology [9] , agriculture [10] , transportation [11] and other fields.…”