Jamming Attack Classification in Wireless Networks Using Machine Learning

R. Arathy, Bidisha Bhabani, Madhuri Malakar, Judhistir Mahapatro, Pushpendu Kar

Research output: Chapter in Book/Conference proceedingConference contributionpeer-review


In the field of wireless networks, jamming exhibits severe security threat by creating deliberate network interference. Detection of presence of jammers as well as distinguishing them is important to allow the network to implement combat strategies more efficiently. A unique defence approach needs to be used for each type of jammers making the classification of jammers even more crucial. In this regards, we have used various network parameters to detect and classify them into the constant, random, and reactive categories. We have used machine learning techniques such as decision tree classifier and random forest classifier, and deep learning techniques such as longest short-term memory and multi-layer perceptron for the classification. Accuracy of multi-layer perceptron being 87% is the maximum among all techniques used.

Original languageEnglish
Title of host publicationCommunication and Intelligent Systems - Proceedings of ICCIS 2022
EditorsHarish Sharma, Vivek Shrivastava, Kusum Kumari Bharti, Lipo Wang
PublisherSpringer Science and Business Media Deutschland GmbH
Number of pages15
ISBN (Print)9789819923212
Publication statusPublished - 2023
Event4th International Conference on Communication and Intelligent Systems, ICCIS 2022 - New Delhi, India
Duration: 19 Dec 202220 Dec 2022

Publication series

NameLecture Notes in Networks and Systems
Volume689 LNNS
ISSN (Print)2367-3370
ISSN (Electronic)2367-3389


Conference4th International Conference on Communication and Intelligent Systems, ICCIS 2022
CityNew Delhi


  • Deep learning
  • Jamming attacks
  • Jamming classification
  • Machine learning

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Signal Processing
  • Computer Networks and Communications


Dive into the research topics of 'Jamming Attack Classification in Wireless Networks Using Machine Learning'. Together they form a unique fingerprint.

Cite this