Counterfeit IC Detection Research Based on Wavelet Transform and SVM
Jia-Wei Ma, Xiongwei Li · 2019
In view of the non-stationary characteristics of the electromagnetic (EM) side channel signal, this paper uses the EM probe and oscilloscope to collect the EM side channel signal of the chip, analyzes the signal by wavelet transform, extracts the wavelet coefficient as the signal feature, and uses the support vector machine to complete the classification of the four chip types. Experiments show that this method can identify the chip model quickly, stably and low-cost. The experiment achieved the expected results. The average correct rate reaches 91.625%.