Open AccessHardware Trojan detection research based on MLP
Author(s) -
Qiao Ding,
Shizhuang Yin,
Lijun Liu,
Chao Wang
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1684/1/012065
Subject(s) - trojan , support vector machine , computer science , field programmable gate array , artificial neural network , feature extraction , artificial intelligence , pattern recognition (psychology) , channel (broadcasting) , set (abstract data type) , feature (linguistics) , hardware trojan , machine learning , embedded system , computer security , telecommunications , linguistics , philosophy , programming language
In view of the variety of Hardware Trojan (HT) and the difficulty of obtaining unknown Trojan characteristics in side-channel signals by conventional methods. In this paper, MLP was selected to establish the network model by means of supervised learning, the method took supervised learning ways to build neural network model for feature extraction and discrimination of side channel information. A verification system was set up based on FPGA to obtain side-channel information. The results show that the detection rate of the MLP is more than 1% higher than that of the traditional support vector machine (SVM) method when detecting the hardware Trojan horse with the parent circuit area of 2%.