A SUPPORT VECTOR MACHINE FOR IDENTIFICATION OF MONITORS BASED ON THEIR UNINTENDED ELECTROMAGNETIC EMANATION
Fan Mo, Yinghua Lu, Zhang Jin-ling, Qiang Cui, Sihai Qiu · Progress In Electromagnetics Research M · 2013
Abstract—Electrical equipments usually radiate unintended emission which carries characteristic information when running, such as emana-tion from computers monitors, keyboards and other components, this emanation can be possibly used to reconstruct the source information. Most of the experiments related to this area are carried out inside a semi-anechoic chamber, and measurement out of it may not be consid-ered to be optimal, because the data captured are usually not sufficient. Yet in this study, we take LCD monitors as typical examples and find that characteristics significantly differ between products, parameters such as the magnitude and spectrum were measured under normal en-vironment. We take the PCB traces as antennas and acquire the raw signal directly near the antenna and extract the parameters to use as input to support vector machine (SVM) which was trained to iden-tify the emanating source (LCD monitors). In this study, the method was tested using the emission captured from one Samsung (SyncMas-ter E1920) and two LG (L1753s) monitors, and a laptop (ACER As-pire 5542). The SVM was able to classify the source of signals with 98.9510 % accuracy while using emission that captured from the run-ning monitors. 1.