TY - GEN
T1 - Hardware-Trojan Detection at Gate-level Netlists using Gradient Boosting Decision Tree Models
AU - Negishi, Ryotaro
AU - Kurihara, Tatsuki
AU - Togawa, Nozomu
N1 - Funding Information:
ACKNOWLEDGMENT This paper is part of the results of projects “Research and Development of AI-Based Chip Vulnerability Inspection Methods in Design and Manufacturing” (PRISM, Cabinet Office, Government of Japan in FY2019) and “The contract of research for detection techniques of hardware vulnerabilities” (Ministry of Internal Affairs and Communication in FY2020–FY2022).
Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - Technological devices including consumer devices have become deeply embedded in people's lives, and their demand is growing every year. It has been indicated that outsourcing the design and manufacturing of ICs, which are essential for tech-nological devices, may lead to the insertion of hardware Trojans. This paper proposes a hardware-Trojan detection method at gate-level netlists based on the gradient boosting decision tree models. We firstly propose the optimal set of Trojan features among many feature candidates at a netlist level through thorough evaluations. Then, we evaluate various gradient boosting decision tree models and determine XGBoost is the best for hardware-Trojan detection. Finally, we construct an XGBoost-based hardware-Trojan detection method with its optimized hyperparameters. Evaluation experiments were conducted on the netlists from Trust-HUB benchmarks and showed the average F-measure of 0.842 using the proposed method. This value is 0.175 points higher than that of the existing best method.
AB - Technological devices including consumer devices have become deeply embedded in people's lives, and their demand is growing every year. It has been indicated that outsourcing the design and manufacturing of ICs, which are essential for tech-nological devices, may lead to the insertion of hardware Trojans. This paper proposes a hardware-Trojan detection method at gate-level netlists based on the gradient boosting decision tree models. We firstly propose the optimal set of Trojan features among many feature candidates at a netlist level through thorough evaluations. Then, we evaluate various gradient boosting decision tree models and determine XGBoost is the best for hardware-Trojan detection. Finally, we construct an XGBoost-based hardware-Trojan detection method with its optimized hyperparameters. Evaluation experiments were conducted on the netlists from Trust-HUB benchmarks and showed the average F-measure of 0.842 using the proposed method. This value is 0.175 points higher than that of the existing best method.
KW - gradient boosting decision tree
KW - hardware security
KW - hardware Trojan
KW - machine learning
KW - netlist
KW - XGBoost
UR - http://www.scopus.com/inward/record.url?scp=85142336972&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85142336972&partnerID=8YFLogxK
U2 - 10.1109/ICCE-Berlin56473.2022.9937099
DO - 10.1109/ICCE-Berlin56473.2022.9937099
M3 - Conference contribution
AN - SCOPUS:85142336972
T3 - IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin
BT - 2022 IEEE 12th International Conference on Consumer Electronics, ICCE-Berlin 2022
PB - IEEE Computer Society
T2 - 12th IEEE International Conference on Consumer Electronics, ICCE-Berlin 2022
Y2 - 2 September 2022 through 6 September 2022
ER -