The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Os dispositivos tecnológicos estão profundamente enraizados na vida das pessoas e a sua procura cresce todos os anos. Foi indicado que a terceirização do projeto e fabricação de circuitos integrados, essenciais para dispositivos tecnológicos, pode levar à inserção de circuitos maliciosos, chamados de Trojans de hardware (HTs). Este artigo propõe um método de detecção de HT em netlists de nível de porta baseado em XGBoost, um dos melhores modelos de árvore de decisão com aumento de gradiente. Primeiro propomos o conjunto ideal de recursos HT entre muitos candidatos a recursos em nível de netlist por meio de avaliações completas. Em seguida, construímos um método de detecção HT baseado em XGBoost com seus hiperparâmetros otimizados. Experimentos de avaliação foram conduzidos nas netlists dos benchmarks Trust-HUB e mostraram a medida F média de 0.842 usando o método proposto. Além disso, propomos recentemente um método de propagação de probabilidade de Trojan que corrige efetivamente os resultados da detecção de HT e o aplica aos resultados obtidos pela detecção de HT baseada em XGBoost. Experimentos de avaliação mostraram que a medida F média melhorou para 0.861. Este valor é 0.194 pontos superior ao do melhor método existente proposto até agora.
Ryotaro NEGISHI
Waseda University
Tatsuki KURIHARA
Waseda University
Nozomu TOGAWA
Waseda University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Ryotaro NEGISHI, Tatsuki KURIHARA, Nozomu TOGAWA, "Hardware-Trojan Detection at Gate-Level Netlists Using a Gradient Boosting Decision Tree Model and Its Extension Using Trojan Probability Propagation" in IEICE TRANSACTIONS on Fundamentals,
vol. E107-A, no. 1, pp. 63-74, January 2024, doi: 10.1587/transfun.2023KEP0005.
Abstract: Technological 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 integrated circuits, which are essential for technological devices, may lead to the insertion of malicious circuitry, called hardware Trojans (HTs). This paper proposes an HT detection method at gate-level netlists based on XGBoost, one of the best gradient boosting decision tree models. We first propose the optimal set of HT features among many feature candidates at a netlist level through thorough evaluations. Then, we construct an XGBoost-based HT 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. Also, we newly propose a Trojan probability propagation method that effectively corrects the HT detection results and apply it to the results obtained by XGBoost-based HT detection. Evaluation experiments showed that the average F-measure is improved to 0.861. This value is 0.194 points higher than that of the existing best method proposed so far.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.2023KEP0005/_p
Copiar
@ARTICLE{e107-a_1_63,
author={Ryotaro NEGISHI, Tatsuki KURIHARA, Nozomu TOGAWA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Hardware-Trojan Detection at Gate-Level Netlists Using a Gradient Boosting Decision Tree Model and Its Extension Using Trojan Probability Propagation},
year={2024},
volume={E107-A},
number={1},
pages={63-74},
abstract={Technological 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 integrated circuits, which are essential for technological devices, may lead to the insertion of malicious circuitry, called hardware Trojans (HTs). This paper proposes an HT detection method at gate-level netlists based on XGBoost, one of the best gradient boosting decision tree models. We first propose the optimal set of HT features among many feature candidates at a netlist level through thorough evaluations. Then, we construct an XGBoost-based HT 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. Also, we newly propose a Trojan probability propagation method that effectively corrects the HT detection results and apply it to the results obtained by XGBoost-based HT detection. Evaluation experiments showed that the average F-measure is improved to 0.861. This value is 0.194 points higher than that of the existing best method proposed so far.},
keywords={},
doi={10.1587/transfun.2023KEP0005},
ISSN={1745-1337},
month={January},}
Copiar
TY - JOUR
TI - Hardware-Trojan Detection at Gate-Level Netlists Using a Gradient Boosting Decision Tree Model and Its Extension Using Trojan Probability Propagation
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 63
EP - 74
AU - Ryotaro NEGISHI
AU - Tatsuki KURIHARA
AU - Nozomu TOGAWA
PY - 2024
DO - 10.1587/transfun.2023KEP0005
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E107-A
IS - 1
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - January 2024
AB - Technological 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 integrated circuits, which are essential for technological devices, may lead to the insertion of malicious circuitry, called hardware Trojans (HTs). This paper proposes an HT detection method at gate-level netlists based on XGBoost, one of the best gradient boosting decision tree models. We first propose the optimal set of HT features among many feature candidates at a netlist level through thorough evaluations. Then, we construct an XGBoost-based HT 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. Also, we newly propose a Trojan probability propagation method that effectively corrects the HT detection results and apply it to the results obtained by XGBoost-based HT detection. Evaluation experiments showed that the average F-measure is improved to 0.861. This value is 0.194 points higher than that of the existing best method proposed so far.
ER -