Use subsequent neural network to analyze ICEMI
Shih‐Yi Yuan, Shu-Yao Hsuan, Cheng-You Chang, Bo-Yu Zhu, Si-Rong He, Yuan-Fu Ku, Tzung-Hsien Chen · 2021
Among the security issues of embedded systems, electromagnetic (EM) information leakage problem is difficult to detect and prevent. When the embedded system is operating, different commands will emit different EM signals. In this paper, we propose a NN architecture to analyze the EM leakage and effectively improve the accuracy. Comparing with a previous research, the accuracy is greatly improved from 38% up to 66%.