基于支持向量机的硬件木马检测建模与优化

Research on Hardware Trojans Detection Based on Support Vector Machine

文章在完成木马理论分析和电路设计的基础上,研究机器学习模式分类理论,并将其应用于集成电路侧信道信息的数据处理和分析,构建了基于支持向量机的硬件木马检测模型,同时通过交叉验证的方法进行模型优化。最终在自主设计的FPGA检测平台上进行基于功耗信息的实验验证,在标准电路中植入面积为0.69%的硬件木马,可以使得检测识别率达到98.64%。

In this paper the hardware Trojans theory and circuit design are described firstly,then the machine learning pattern classification theory are studied and applied into the data processing and analysis of side channelin integrated circuits. The two classification detection model of the hardware Trojans will be set up based on Support Vector Machine, and the model will be optimized by Cross Validation method. Finally the experiments are implemented in FPGA platform. When the Trojan circuit of area 0.69% is implanted into the standard circuit, the detection and recognition rate can reach the value of 98.64% according to the CV algorithm.