Scholarlink

<p>With the globalization of the integrated circuit supply chain, the need for Hardware Trojan (HT) detection has become increasingly urgent, but the existing detection methods still face many challenges, such as susceptibility to overfitting and inefficient detection performance. We combine the structural and testability features associated with HTs, followed by integrating the base learners of the local outlier factor and cluster-based local outlier factor to improve the detection performance. The results of leave-one-out cross-validation experiments on the Trust_Hub hardware Trojan library show that the method achieves an average true-positive rate of 66.63%, true-negative rate of 98.01%, precision of 49.94%, F-measure of 54.49%, and accuracy of 97.60%, and outperforms state-of-the-art methods. The outcomes highlight the superior performance of the proposed method and indicate its potential future application.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Stacking ensemble feature-attention LOFs for detecting hardware Trojan

  • 期刊论文

  • 发表日期：

    2025年5月26日

查看全文
  • Tingyuan Nie,
  • Jingjing Nie,
  • Kun Zhao

摘要

With the globalization of the integrated circuit supply chain, the need for Hardware Trojan (HT) detection has become increasingly urgent, but the existing detection methods still face many challenges, such as susceptibility to overfitting and inefficient detection performance. We combine the structural and testability features associated with HTs, followed by integrating the base learners of the local outlier factor and cluster-based local outlier factor to improve the detection performance. The results of leave-one-out cross-validation experiments on the Trust_Hub hardware Trojan library show that the method achieves an average true-positive rate of 66.63%, true-negative rate of 98.01%, precision of 49.94%, F-measure of 54.49%, and accuracy of 97.60%, and outperforms state-of-the-art methods. The outcomes highlight the superior performance of the proposed method and indicate its potential future application.