Manara - Qatar Research Repository
Browse

Real-Time Jamming Detection via Deep Learning

Download (1.33 MB)
thesis
submitted on 2024-10-28, 11:05 and posted on 2024-10-30, 09:34 authored by Rasha Abdulsalam M. Ali
Wireless communication systems are vulnerable to intentional jamming that can result in significant disruptions to critical infrastructure, military communications, and civilian networks. Early detection of such attacks is critical to mitigate their impact and prevent further damage. Classical jamming detection approaches, which are commonly employed in stationary networks, entail the jammed receiver determining the occurrence of the jammer by measuring the impact of the jamming behavior in terms of packet loss and received signal strength. Accordingly, these techniques only allow for post-event analysis. In mobile contexts, such as those involving drones or vehicles, the impact of jamming tends to increase as the receiver moves closer to the source of the interference. Hence, it is possible to detect jamming activity earlier in these scenarios, before any packet loss or other communication issues occur. In this thesis, we investigate the possibility of detecting jamming before it affects the quality of the radio link. We used this approach for early jamming detection in mobile context to anticipate events and prevent losing the power of communication, and hence, improving the ability to maintain real-time awareness and resilience. We executed a comprehensive data collection process, as a result, by adjusting different scenario setup parameters, this method can detect the existence of a jammer with a precision more than 0.99,Despite the fact that the bit error rate is zero (below 0.01), early detection is possible.

History

Language

  • English

Publication Year

  • 2023

License statement

© The author. The author has granted HBKU and Qatar Foundation a non-exclusive, worldwide, perpetual, irrevocable, royalty-free license to reproduce, display and distribute the manuscript in whole or in part in any form to be posted in digital or print format and made available to the public at no charge. Unless otherwise specified in the copyright statement or the metadata, all rights are reserved by the copyright holder. For permission to reuse content, please contact the author.

Institution affiliated with

  • Hamad Bin Khalifa University
  • College of Science and Engineering - HBKU

Degree Date

  • 2023

Degree Type

  • Master's

Advisors

Gabriele Oligeri

Committee Members

Roberto Di Pietro ; Gabriel Ghinita

Department/Program

College of Science & Engineering

Usage metrics

    College of Science and Engineering - HBKU

    Categories

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC