信息网络安全 ›› 2017, Vol. 17 ›› Issue (8): 33-38.doi: 10.3969/j.issn.1671-1122.2017.08.005

• • 上一篇    下一篇

基于支持向量机的硬件木马检测建模与优化

苏静1,2(), 路文玲3, 赵毅强1, 史艳翠2   

  1. 1.天津大学微电子学院,天津 300072
    2.天津科技大学计算机科学与信息工程学院,天津 300222
    3.天津城市职业学院机电与信息工程系,天津 300250
  • 收稿日期:2017-05-19 出版日期:2017-08-20 发布日期:2020-05-12
  • 作者简介:

    作者简介: 苏静(1979—),女,北京,副教授,博士研究生,主要研究方向为信息安全、智能信息处理;路文玲(1971—) ,女,天津,副教授,硕士,主要研究方向为电路设计、嵌入式系统;赵毅强(1964—) ,男,河北,教授,博士,主要研究方向为信息安全、硬件木马;史艳翠(1982—) ,女,河北,讲师,博士研究生,主要研究方向为智能信息处理。

  • 基金资助:
    国家自然科学基金 [61376032,61402331];天津市自然科学基金重点资助项目[12JCZDJC20500]

Research on Hardware Trojans Detection Based on Support Vector Machine

Jing SU1,2(), Wenling LU3, Yiqiang ZHAO1, Yancui SHI2   

  1. 1. School of Microelectronics, Tianjin University 300072, China
    2. College of Computer Science and Information Engineering, Tianjin University of Sci&Tech, Tianjin 300222, China
    3. Department of Electronic Information Engineering, Tianjin City Vocational College, Tianjin 300250, China
  • Received:2017-05-19 Online:2017-08-20 Published:2020-05-12

摘要:

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%。

关键词: 硬件木马, 侧信道分析, 支持向量机, 交叉验证

Abstract:

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.

Key words: hardware Trojans, side-channel analysis, support vector machine, cross validation

中图分类号: