Hardware-Trojan Detection at Gate-level Netlists using Gradient Boosting Decision Tree Models

Negishi, Ryotaro; Kurihara, Tatsuki; Togawa, Nozomu

doi:10.1109/icce-berlin56473.2022.9937099

Cited by 3 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2. In HT detection based on machine learning using gate-level netlist features, the learning process extracts HT features for every net in a given † The preliminary version of this paper appeared in [9]. The main extensions are summarized as follows: We propose a Trojan probability propagation method and its evaluation results in Sect.…”

Section: Flow Of Ht Detectionmentioning

confidence: 99%

See 1 more Smart Citation

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

Negishi

Kurihara

Togawa

2024

IEICE Trans. Fundamentals

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Flow Of Ht Detectionmentioning

confidence: 99%

“…According to [9], we evaluate the machine learning model by leave-one-out cross validation. In other words, when evaluating a netlist N in Table 3, we train the machine learning model on the remaining 31 netlists, and then for each net in N, we identify whether the net is a Trojan net or a normal net.…”

Section: Ht Detection Using Xgboostmentioning

confidence: 99%