An Adaptive Security Data Collection and Composition Recognition method for security measurement over LTE/LTE-A networks. (1st April 2020)

• Record Type: Journal Article
• Authors: Fu, Yulong; Chen, Hanlu; Zheng, Qinghua; Yan, Zheng; Kantola, Raimo; Jing, Xuyang; Cao, Jin; Li, Hui
• Is Part Of: Journal of network and computer applications. Volume 155(2020)
• Publication Date: 2020-04-01
• Subjects: Security measurement -- LTE network security -- Data collection algorithm -- Data composition algorithm -- NS3 simulation -- Data processing; Microcomputers -- Periodicals; Computer networks -- Periodicals; Application software -- Periodicals; Micro-ordinateurs -- Périodiques; Réseaux d'ordinateurs -- Périodiques; Logiciels d'application -- Périodiques; Application software; Computer networks; Microcomputers; Periodicals; 004.05; 004
• DOI: 10.1016/j.jnca.2020.102549
• Languages: English
• ISSNs: 1084-8045

Abstract

Abstract: With the development of wireless communications, Mobile Networks have become an important part of our daily life and fueled the growth of many attractive technologies such as 5G, Internet of Things (IoT) and even Smart City. As a main bearer of current Mobile Networks, LTE/LTE-A carries massive and important business data but is facing more and more serious attack situations, which makes the Security Measurement over it become necessary and important. However, current methods are usually designed from specific malicious detections, which cannot provide the user with a synthetic view of security evaluation. Meanwhile, as the massive amount and poor quality of networking data are considered, the efficiency and accuracy of the current security measurement methods are usually not good. In this paper, we focus on the evaluation basis (the collecting data) of security measurement over LTE/LTE-A networks, and propose an Adaptive Security Data Collection and Composition Recognition (ASDCCR) method for it. We design heuristic algorithms and processing framework in ASDCCR to make the data collection adaptive and synthetic attack recognition become possible. We also verified the proposed method in simulated LTE environment of NS3 to verify the usability and accuracy of the proposed methods. Highlights: A feature selection algorithm based on Partial Mutual Information Gain. A heuristic mechanism to adaptively adjust data collection strategies. A Serial and Parallel Structure for synthetic attack class recognition. A structure for security data collection and composition recognition.