Machine Learning Threatens 5G Security

Jani Suomalainen (Corresponding Author), Arto Juhola, Shahriar Shahabuddin, Aarne Mämmelä, Ijaz Ahmad

Research output: Contribution to journalArticleScientificpeer-review

36 Citations (Scopus)
576 Downloads (Pure)


Machine learning (ML) is expected to solve many challenges in the fifth generation (5G) of mobile networks. However, ML will also open the network to several serious cybersecurity vulnerabilities. Most of the learning in ML happens through data gathered from the environment. Un-scrutinized data will have serious consequences on machines absorbing the data to produce actionable intelligence for the network. Scrutinizing the data, on the other hand, opens privacy challenges. Unfortunately, most of the ML systems are borrowed from other disciplines that provide excellent results in small closed environments. The resulting deployment of such ML systems in 5G can inadvertently open the network to serious security challenges such as unfair use of resources, denial of service, as well as leakage of private and confidential information. Therefore, in this article we dig into the weaknesses of the most prominent ML systems that are currently vigorously researched for deployment in 5G. We further classify and survey solutions for avoiding such pitfalls of ML in 5G systems.
Original languageEnglish
Pages (from-to)190822 - 190842
JournalIEEE Access
Publication statusPublished - Oct 2020
MoE publication typeA1 Journal article-refereed


  • 5G
  • cybersecurity
  • machine learning
  • mobile networks
  • survey
  • threats
  • vulnerabilities
  • wireless networks


Dive into the research topics of 'Machine Learning Threatens 5G Security'. Together they form a unique fingerprint.

Cite this