Research on Hardware Trojans Detection Based on Support Vector Machine

doi:10.3969/j.issn.1671-1122.2017.08.005

Abstract

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

CLC Number:

TP309

Jing SU, Wenling LU, Yiqiang ZHAO, Yancui SHI. Research on Hardware Trojans Detection Based on Support Vector Machine[J]. Netinfo Security, 2017, 17(8): 33-38.

Figures/Tables 7

References 17

[1]	KARRI R, RAJENDRAN J, ROSENFELD K, et al.Toward Trusted Hardware: Identifying and Classifying Hardware Trojans[J].Computer, 2011, 44(7):66-74.
[2]	CLARK J, LEBLANC S, KNIGHT S.Hardware Trojan Horse Device Based on Unintended Usb Channels[C]//IEEE. NSS '09 Proceedings of the 2009 Third International Conference on Network and System Security,October 19 - 21, 2009,Gold Coast, Queensland, Australia. New York:IEEE, 2009 :1-8.
[3]	CLARK J,LEBLANC S,Knight S.Risks Associated with USB Hardware Trojan Devices Used by Insiders[C]// IEEE. 2011 5th IEEE International Systems Conference,April 4-7,2011,Montreal, QC, Canada. New York:IEEE,2011:201-208.
[4]	KARRI R,RAJENDRAN J,ROSENFELD K, et al.Trustworthy Hardware: Identifying and Classifying Hardware Trojans[J].Computer, 2010, 43(10):39-46.
[5]	BANGA M,HSIAO M S.A Region Based Approach for the Identification of Hardware Trojans[C]// IEEE. HST '08 Proceedings of the 2008 IEEE International Workshop on Hardware-Oriented Security and Trust,June 9, 2008,Anaheim, CA, USA. Washington: IEEE Computer Society, 2008:40-47.
[6]	WANG X X,SALMANI H,TEHRANJPOOR M,et al.Hardware Trojan Detection and Isolation Using Current Integration and Localized Current Analysis[C]//IEEE. 2012 IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems,October 1-3, 2008,Boston, MA, USA.New York:IEEE,2008:87-95.
[7]	AGRAWAL D,BAKTIR S,ARAKOYUNLU D, et al.Trojan Detection Using IC Fingerprinting[C]// IEEE .IEEE Symposium on Security and Privacy,May 20 - 23, 2007 ,Berkeley, CA, USA. New York:IEEE,2007:296-310.
[8]	张鹏,王新成,周庆.基于投影寻踪分析的芯片硬件木马检测[J].通信学报,2013,34(4):122-126.
[9]	刘长龙,赵毅强,史亚峰,等.基于相关性分析的硬件木马检测方法[J].计算机工程,2013, 39(9):183-185.
[10]	王力纬,贾鲲鹏,方文啸,等.基于马氏距离的硬件木马检测方法[J].微电子学,2013(6):817-820.
[11]	赵毅强,杨松,何家骥,等.基于主成分分析的硬件木马检测方法[J].华中科技大学学报(自然科学版), 2015, 43(8):66-69.
[12]	刘长龙,赵毅强,史亚峰,等.基于侧信道分析的硬件木马的建模与优化[J].华中科技大学学报(自然科学版), 2013, 41(2):53-57.
[13]	吴晓萍,赵学靖,乔辉,等.基于LASSO-SVM的软件缺陷预测模型研究[J].计算机应用研究,2013,43(8):66-69.
[14]	刘长龙. 基于侧信道分析的硬件木马检测方法研究[D].天津:天津大学,2013.
[15]	王庆,屠晨阳,沈嘉荟. 侧信道攻击通用框架设计及应用[J]. 信息网络安全,2017(5):57-62.
[16]	冯紫竹. 基于侧信道分析的硬件木马检测平台设计[D].天津:天津大学,2013.
[17]	周昱,于宗光. 硬件木马威胁与识别技术综述[J]. 信息网络安全,2016(1):11-17.