Publication Date

1-1-2022

Document Type

Conference Proceeding

Publication Title

Communications in Computer and Information Science

Volume

1683 CCIS

DOI

10.1007/978-3-031-24049-2_7

First Page

107

Last Page

119

Abstract

Performance prediction in wireless mobile networks is essential for diverse purposes in network management and operation. Particularly, the position of mobile devices is crucial to estimating the performance in the mobile communication setting. With its importance, this paper investigates mobile communication performance based on the coordinate information of mobile devices. We analyze a recent 5G data collection and examine the feasibility of location-based performance prediction. As location information is key to performance prediction, the basic assumption of making a relevant prediction is the correctness of the coordinate information of devices given. With its criticality, this paper also investigates the impact of position falsification on the ML-based performance predictor, which reveals the significant degradation of the prediction performance under such attacks, suggesting the need for effective defense mechanisms against location spoofing threats.

Funding Sponsor

Ministry of Science, ICT and Future Planning

Keywords

Location spoofing, Machine learning, Mobile networks, Performance prediction, Position falsification

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.

Department

Computer Engineering

Share

COinS