Novel Design of Hardware Trojan: A Generic Approach for Defeating Testability Based Detection

Zhang, Ning; Lv, Zhiqiang; Zhang, Yanlin; Li, Haiyang; Zhang, Yixin; Huang, Weiqing

doi:10.1109/trustcom50675.2020.00034

Cited by 5 publications

(6 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further, to make the DeTrust benchmarks [13], we perform the modification in 10 Trust-Hub benchmarks by inserting the one flipflop at each gate output of the trigger circuit as suggested by [20]. Similarly, to show the Trojan designed by DeTest [29], we modify the one Trust-Hub benchmark s38417−T 100 by inserting the given logic in this circuit. Finally, [20] also suggests to make always-on-Trojan by removing the trigger part of the Trust-Hub s38417 − T 300 benchmark whose payload is a ring oscillator Trojan.…”

Section: A Dataset Description and Evaluation Measuresmentioning

confidence: 99%

Structural and SCOAP features based approach for hardware Trojan detection using SHAP and Light Gradient Boosting model

Sharma¹,

Sharma²,

Pattanaik³

et al. 2023

Preprint

View full text Add to dashboard Cite

<p>Hardware Trojan (HT) is the most critical threat due to outsourcing of Integrated circuit designing phases. Therefore, a new technique is proposed that utilizes structural and SCOAP features to detect HT from the gate-level netlist using Light Gradient Boosting (Light GBM). Further, a model agnostic Shapley additive explanations (SHAP) is employed to identify each feature global and local impact on model prediction. Moreover, a quartile-based feature selection method is proposed, which uses SHAP to identify the optimal feature set by keeping low retraining rounds. Experimental results show that the proposed technique accurately detects always-on-Trojans and HT nets from Trust-Hub, DeTrust, and DeTest benchmarks.</p>

show abstract

Section: A Dataset Description and Evaluation Measuresmentioning

confidence: 99%

Structural and SCOAP features based approach for hardware Trojan detection using SHAP and Light Gradient Boosting model

Sharma¹,

Sharma²,

Pattanaik³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Finally, the clustering results are fed to the decision-making system, which identifies the circuits as Trojan-free/inserted based on the majority voting scheme. Recently, DeTest [29] defeated SCOAP based techniques by designing new Trojans, which decreases the SCOAP values of HT nets up to 10%. Moreover, structural/SCOAP featuresbased techniques fail to detect either always-on-Trojans or low SCOAP HT nets.…”

Section: Literature Review: Analysismentioning

confidence: 99%

Section: A Dataset Description and Evaluation Measuresmentioning

confidence: 99%

Structural and SCOAP Features Based Approach for Hardware Trojan Detection Using SHAP and Light Gradient Boosting Model

Sharma,

Pattanaik

et al. 2023

J Electron Test

View full text Add to dashboard Cite

Hardware Trojan (HT) is the most critical threat due to outsourcing of Integrated circuit designing phases. Therefore, a new technique is proposed that utilizes structural and SCOAP features to detect HT from the gate-level netlist using Light Gradient Boosting (Light GBM). Further, a model agnostic Shapley additive explanations (SHAP) is employed to identify each feature global and local impact on model prediction. Moreover, a quartile-based feature selection method is proposed, which uses SHAP to identify the optimal feature set by keeping low retraining rounds. Experimental results show that the proposed technique accurately detects always-on-Trojans and HT nets from Trust-Hub, DeTrust, and DeTest benchmarks.

show abstract

“…Unsupervised strategies, in general, adopt testability measurebased features targeting Trojans that have low controllability and low observability [30]. Such methods can be circumvented by redesigning the Trojans to satisfy the conditions of a normal circuit, as mentioned in [21]. Furthermore, strategies that adopt structural features underperform in true positive rate (TPR) due to the limited Trojan space learned in the training phase, causing poor generalization capability.…”

Section: Related Workmentioning

confidence: 99%

“…On the other hand, unsupervised strategies use functional features, targeting Trojans with low controllability and transition probability pertaining to their stealthy nature. Such methods can be evaded by redesigning Trojans to satisfy the conditions of a normal circuit [21]. Moreover, the methods that depend on structural features underperform in true positive rate (TPR) due to the limited Trojan space exploration in the training phase.…”

mentioning

confidence: 99%

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

Sankar

Jayakumar

2022

IEEE Access

View full text Add to dashboard Cite

IoT devices handle a large amount of information including sensitive information pertaining to the deployed application. Such a scenario, makes IoT devices susceptible to various attacks. In addition to securing IoT devices, it is equally important to secure communication among devices and with the outside world. RS232 is a common communication protocol used in IoT and embedded devices. Hence ensuring, Trojan detection in RS232 plays a major role in providing secured communication among edge assisted IoT devices. The inclusion of malicious circuits known as hardware Trojans can occur at any stage of the IC design and manufacturing. Existing pre-silicon detection schemes with static features is limited by the number of features that are learned by the detection scheme. In contrast, machine learning allows enhanced Trojan space exploration. Existing machine learning-based Trojan detection consists primarily of supervised algorithms that rely on high-quality labeled datasets for efficient Trojan detection. Unsupervised methods, on the other hand, underperform due to limited training data and severe imbalance within the available data. To handle such a situation, a semi-supervised hardware Trojan detection has been proposed. In this work, permutation importance guided principal component analysis, correlation aware data augmentation, and hyper-parameter optimization using genetic algorithm aid in optimal dataset and model generation. Pseudo label generation using semi-supervised schemes is utilized to handle partially labeled datasets. For the Trust-HUB benchmarks, the proposed methodology achieves an average of 88.48% true positive rate and 95.77% true negative rate which, clearly indicates the effectiveness and feasibility of semi-supervised hardware Trojan detection. INDEX TERMSSemi-supervised algorithm, hardware Trojan detection, correlation-aware data augmentation, hyper-parameter optimization, genetic algorithm, permutation importance, XGBoost I. INTRODUCTION T HE rapid advancement in microelectronic technologies has led to the exploration of cloud computing, big data, artificial intelligence, embedded systems, 5G communication and internet of things (IoT). IoT extends from smart city to smart healthcare including many mission critical systems.IoT framework consists of sensors, actuators and embedded electronic devices that receive, store and transmit data. As per forecast, the number of connected smart devices will reach 75 billion by 2025 [1]. When the number of connected devices grow, there exists a multi-fold increase in the data to be handled. In such a scenario, quality of service (QoS)

show abstract

Novel Design of Hardware Trojan: A Generic Approach for Defeating Testability Based Detection

Cited by 5 publications

References 21 publications

Structural and SCOAP features based approach for hardware Trojan detection using SHAP and Light Gradient Boosting model

Structural and SCOAP features based approach for hardware Trojan detection using SHAP and Light Gradient Boosting model

Structural and SCOAP Features Based Approach for Hardware Trojan Detection Using SHAP and Light Gradient Boosting Model

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

Contact Info

Product

Resources

About