2020/04/13 by Marouane Hachimi, Hachimi, Marouane, Georges Kaddoum +5 · 3 citations
Computer Science · #FOS: Computer and information sciences #Internet Traffic Analysis and Secure E-voting #Machine Learning (cs.LG) #Network Security and Intrusion Detection #Networking and Internet Architecture (cs.NI) #Security in Wireless Sensor Networks
paper · pdf · doi:10.48550/arxiv.2004.06077
openalex publication_date 2020/04/13 · openalex created_date 2022/07/26 · openalex updated_date 2026/07/28
In 5G networks, the Cloud Radio Access Network (C-RAN) is considered a\npromising future architecture in terms of minimizing energy consumption and\nallocating resources efficiently by providing real-time cloud infrastructures,\ncooperative radio, and centralized data processing. Recently, given their\nvulnerability to malicious attacks, the security of C-RAN networks has\nattracted significant attention. Among various anomaly-based intrusion\ndetection techniques, the most promising one is the machine learning-based\nintrusion detection as it learns without human assistance and adjusts actions\naccordingly. In this direction, many solutions have been proposed, but they\nshow either low accuracy in terms of attack classification or they offer just a\nsingle layer of attack detection. This research focuses on deploying a\nmulti-stage machine learning-based intrusion detection (ML-IDS) in 5G C-RAN\nthat can detect and classify four types of jamming attacks: constant jamming,\nrandom jamming, deceptive jamming, and reactive jamming. This deployment\nenhances security by minimizing the false negatives in C-RAN architectures. The\nexperimental evaluation of the proposed solution is carried out using WSN-DS\n(Wireless Sensor Networks DataSet), which is a dedicated wireless dataset for\nintrusion detection. The final classification accuracy of attacks is 94.51 %\nwith a 7.84 % false negative rate.\n