A method to detect and locate the character information submerged in electromagnetic leakage signal
Weiqing Huang, Zhao Jianlin, Zhiqiang Lv, Ding Xuejie, Wang Lei · 2016 IEEE Information Technology, Networking, Electronic and Automation Control Conference · 2016
Electromagnetic emission from information technology equipment (ITE) can cause the information leakage. The eavesdroppers can reconstruct the information operated on the marked equipment by eavesdropping the electromagnetic radiation. In this paper, we design a method to detect whether existing character information in the leakage signal and located them automatically using machine learning algorithms. Gabor filter is used to extract the features of the electromagnetic leakage signal and relevance vector machine (RVM) is used to learn these features and make prediction for test signal. This method can also be used in the receiving system for electromagnetic leakage and guide to which signal is important to process. The experiment result show that this method can detect and locate the sensitive information submerged in electromagnetic leakage signal properly.