The integration of the Internet of Things (IoT),5G and satellite technologies has evolved telecommunicationnetworks to provide higher quality and more stable service toremote areas. However security concerns with IoT are growingas IoT devices become increasingly attractive targets for cyberattacks due to hugely growing volumes and also poor or non-existent inbuilt security. In this paper, we propose a IoT andsatellite based 5G network security model which is able to harnessmachine learning to provide more effective detection of cyberattacks and malware. The solution is divided into two main parts.The creation of the model for intrusion detection using variousmachine learning (ML) algorithms and the implementation ofthis ML based model into terrestrial or satellite gateways. Thispaper will demonstrate that ML algorithms can be used toclassify benign or malicious packets in an IoT network to enhancesecurity. Finally, the tested ML algorithms are compared foreffectiveness in terms of accuracy rate, precision, recall, f1-scoreand false negative rate.Index Terms—Satellite, IoT, Security, Machine learning, Intru-sion Detection System, cybersecurity attacks, security automa-tion, software defined security.
|Publication status||Submitted - 15 Nov 2019|