Increasing the Sensitivity of the Method of Early Detection of Cyber-Attacks in Telecommunication Networks Based on Traffic Analysis by Extreme Filtering

作     者：Privalov, Andrey Lukicheva, Vera Kotenko, Igor Saenko, Igor 

作者机构：Emperor Alexander I St Petersburg State Transport 9 Moskovsky Pr St Petersburg 190031 Russia Russian Acad Sci SPIIRAS St Petersburg Inst Informat & Automat 3914 Liniya St Petersburg 199178 Russia 

出 版 物：《ENERGIES》 (能源)

年 卷 期：2020年第13卷第11期

页      面：2774页

核心收录：

学科分类：0820[工学-石油与天然气工程] 08[工学] 0807[工学-动力工程及工程热物理] 

基　　金：RSF [18-11-00302] Russian Science Foundation [18-11-00302] Funding Source: Russian Science Foundation 

主　　题：detection of cyberattacks extreme filtering traffic decomposition fuzzy logic algorithm 

摘      要：The paper proposes a method for improving the accuracy of early detection of cyber attacks with a small impact, in which the mathematical expectation is a fraction of the total, and the pulse repetition period is quite long. Early detection of attacks against telecommunication networks is based on traffic analysis using extreme filtering. The algorithm of fuzzy logic for deciding on the results of extreme filtering is suggested. The results of an experimental evaluation of the proposed method are presented. They demonstrate that the method is sensitive even with minor effects. In order to eliminate the redundancy of the analyzed parameters, it is enough to use the standard deviation and the correlation interval for decision making.