| 基于级联结构特征的硬件木马检测方法 |
| |
| 引用本文： | 陈嘉伟,刘鸿瑾,张绍林,李宾,李康,温聪,周游,潘伟涛,史江义.基于级联结构特征的硬件木马检测方法[J].微电子学,2023,53(1):164-169. |
| |
| 作者姓名： | 陈嘉伟 刘鸿瑾 张绍林 李宾 李康 温聪 周游 潘伟涛 史江义 |
| |
| 作者单位： | 西安电子科技大学 微电子学院, 西安 710071;北京轩宇空间科技有限公司, 北京 100190;西安电子科技大学 综合业务网理论及关键技术国家重点实验室, 西安 710071 |
| |
| 基金项目： | 西安电子科技大学校企合作项目(HX07202012009) |
| |
| 摘 要： | 针对基于静态结构特征的机器学习方法对门级硬件木马检测结果检测率不高的问题，提出了一种基于级联结构特征的硬件木马检测方法。利用共现矩阵进行特征构建，并使用多对多结构的堆叠式长短期记忆网络(Long Short-Term Memory, LSTM)进行木马特征的训练与识别。实验结果表明，该方法在Trusthub的15个基准网表中获得了93.1%的平均真阳性率(TPR)、99.0%的平均真阴性率(TNR)和79.3%的F1-score。实验结果优于现有方法。
|
| 关 键 词： | 硬件木马 长短期记忆 硬件木马检测 门级网表 |
| 收稿时间： | 2021/12/16 0:00:00 |
A Hardware Trojan Detection Method Based on Cascade Structure |
| |
| CHEN Jiawei,LIU Hongjin,ZHANG Shaolin,LI Bin,LI Kang,WEN Cong,ZHOU You,PAN Weitao,SHI Jiangyi.A Hardware Trojan Detection Method Based on Cascade Structure[J].Microelectronics,2023,53(1):164-169. |
| |
| Authors: | CHEN Jiawei LIU Hongjin ZHANG Shaolin LI Bin LI Kang WEN Cong ZHOU You PAN Weitao SHI Jiangyi |
| |
| Abstract: | The machine learning method based on static structural features has poor detection results for gate-level Hardware Trojans (HT). A HT detection method based on cascaded structure features is proposed. The features are constructed by co-occurrence matrix and are recognized by a many-to-many stacked long short-term memory (LSTM) network. The experimental results show that this method obtains 93.1% of the average true positive rate (TPR), 99.0% of the average true negative rate (TNR) and 79.3% of F1-score in 15 benchmarks from TrustHub. The experimental results are better than the existing methods. |
| |
| Keywords: | hardware trojan long short-term memory (LSTM) HT detection gate-level netlist |
|
| 点击此处可从《微电子学》浏览原始摘要信息 |
| 点击此处可从《微电子学》下载免费的PDF全文 |
|
