Evaluating the Effectiveness of Machine Learning Algorithms in Detecting Distributed Denial of Service Attacks in Mobile Edge Computing

Authors

  • Emmanuel Sibusiso Chaki
  • Sekgoari Semaka Mapunya
  • Emmanuel Sibusiso Chaki
  • Mthulisi Velempini

Keywords:

Distributed Denial of Service , 5G , Machine learning algorithms , Mobile edge computing

Abstract

Mobile Edge Computing (MEC) is the last mile  technology in 5G designed to reduce latency and  to execute delay-sensitive applications closer to  the end-user. MEC is also known as Multi-Access  Edge Computing, which extends the capabilities  of cloud computing to the network's edge and  brings more capabilities closer to the user. By  deploying cloud capabilities to the edge servers,  MEC reduces latency and delay. As a result, the  end-user experience is enhanced. Unfortunately,  the MEC is susceptible to security challenges.  Therefore, security is a challenge that requires  attention. This paper investigates and compares  the effectiveness of machine learning algorithms  designed to detect distributed denial of service  (DDoS) attacks in MEC. DDoS is one of the  security concerns that are negating the advantages  of MEC. It degrades the performance of the  network. In this work, network and application  layer DDoS attacks were considered. The study observed that the Support Vector Machine  outperformed other machine learning techniques, and the findings are fundamental to the  development of our proposed security framework  for MEC.

https://doi.org/10.59200/ICONIC.2022.029

Downloads

Published

2022-12-31