摘要
针对传统芯片检测方法存在检测效率低、要求高、适用性差等问题,提出了基于电磁旁路信号和机器学习方法的伪芯片检测框架.首先,在持有正品芯片的基础上通过引入神经网络和多种特征提取方法提取特征向量,并将正样本的指令信号作为模板库;然后,对待测芯片近场电磁信号进行加窗分帧,并对每帧信号进行特征提取;最后,将特征向量输入改进核函数的一类支持向量机进行扫描式匹配,从而达到芯片检测的目的.实验结果表明,该方法能够适用于以次充好重标记类型的伪芯片检测.
Aiming at the problems of traditional chip detection methods,such as low detection efficiency,high requirements and poor applicability,a chip detection framework based on the electromagnetic side channel and machine learning method is proposed.Firstly,on the basis of holding the genuine chip,the feature vector is extracted by introducing the neural network and various feature extraction methods,and the instruction signal of the positive sample is used as the template library.Then,the near-field electromagnetic signals of the chip to be tested are divided into frames,and the features of each frame are extracted.Finally,the feature vectors are input to One-Class Support Vector Machine with improved kernel function for scanning matching,so as to achieve the purpose of chip detection.The experimental results show that the proposed method can be applied to the detection of counterfeit chips that have been re-marked such as shoddy chips and fake chips.
作者
李雄伟
刘俊延
张阳
陈开颜
刘林云
LI Xiongwei;LIU Junyan;ZHANG Yang;CHEN Kaiyan;LIU Linyun(Shijiazhuang Campus,Army Engineering University,Shijiazhuang 050003,China)
出处
《湖南大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2022年第2期117-124,共8页
Journal of Hunan University:Natural Sciences
基金
国家自然科学基金青年基金资助项目(61602505)。
关键词
集成电路
伪芯片检测
旁路分析
自动编码器
一类支持向量机
integrated circuit
counterfeit chip detection
side channel analysis
auto encoder
One-Class Sup-port Vector Machine
