李鑫, 李海明, 马健. 基于电路结构分析的集成模型检测硬件木马[J]. 微电子学与计算机, 2021, 38(5): 80-86.
引用本文: 李鑫, 李海明, 马健. 基于电路结构分析的集成模型检测硬件木马[J]. 微电子学与计算机, 2021, 38(5): 80-86.
LI Xin, LI Hai-ming, MA Jian. Hardware trojans detection based on circuit structure analysis and integrated model[J]. Microelectronics & Computer, 2021, 38(5): 80-86.
Citation: LI Xin, LI Hai-ming, MA Jian. Hardware trojans detection based on circuit structure analysis and integrated model[J]. Microelectronics & Computer, 2021, 38(5): 80-86.

基于电路结构分析的集成模型检测硬件木马

Hardware trojans detection based on circuit structure analysis and integrated model

  • 摘要: 硬件安全已经成为当今时代备受瞩目的焦点问题,硬件木马检测的技术也逐渐变得多样化.针对硬件木马的检测,本文提出一种基于电路结构分析的集成模型.该方法利用遍历的方法提取硬件木马三组门级特征,采用NLP思想与方法和RobustScaler标准化的预处理,将复杂繁琐的电路图转化为向量数据格式,通过极限梯度提升树和长短期记忆神经网络的集成模型来检测硬件木马.86.5%TPR和97.9%TNR的实验结果,有效说明本方法的高效性和准确性.

     

    Abstract: Hardware security has become the focus of attention in today′s era, hardware Trojans detection techniques are also becoming more diverse. For the detection of hardware Trojans, an integrated model based on circuit structure analysis is proposed in this paper. In this method, three groups of gate level features of hardware Trojan were extracted by topological retrieval, and the complex circuit diagram was transformed into vector data format by NLP idea and method and Robust scaler standardized pretreatment. The hardware Trojan was detected by the integrated model of limit gradient lifting tree and long short memory neural network.The experimental results of 86.5% TPR and 97.9% TNR effectively illustrate the efficiency and accuracy of this method.

     

/

返回文章
返回