Machine Learning Based Physical Layer Security for Detecting Active Eavesdropping Attacks

Cheng Yin; Pei Xiao; Vishal Sharma; Zheng Chu; Emiliano Garcia-Palacios

doi:10.1109/LCOMM.2025.3582157

Machine Learning Based Physical Layer Security for Detecting Active Eavesdropping Attacks

Cheng Yin
, Pei Xiao
, Vishal Sharma
, Zheng Chu
, Emiliano Garcia-Palacios

Research output: Contribution to journal › Article › peer-review

3 Citations (Scopus)

144 Downloads (Pure)

Abstract

This letter explores machine learning for enhancing physical layer security in a wireless system with an access point, legitimate users, and an active eavesdropper. During uplink training, the eavesdropper mimics pilot signals to compromise communication. We propose a framework to extract statistical features from wireless signals and build physical layer datasets. A one-class Support Vector Machine (OC-SVM) is used to detect such active eavesdropping attacks. Additionally, we introduce a twin-class SVM (TC-SVM) model to evaluate and compare detection performance. Simulation results demonstrate that our proposed approach with OC-SVM achieves a detection accuracy of 99.78%, performing favorably compared to the TC-SVM model and other prior methods.

Original language	English
Pages (from-to)	1978-1982
Number of pages	5
Journal	IEEE Communications Letters
Volume	29
Issue number	8
Early online date	23 Jun 2025
DOIs	https://doi.org/10.1109/LCOMM.2025.3582157
Publication status	Published (in print/issue) - 31 Aug 2025

Bibliographical note

Publisher Copyright:
© 1997-2012 IEEE.

Funding

The work of Zheng Chu was supported in part by the Ningbo Natural Science Foundation under Grant 2024J233.

Funder number
2024J233

Keywords

Machine learning
physical layer security
SVM

Access to Document

10.1109/LCOMM.2025.3582157

LCOMM3582157Author Accepted Manuscript, 563 KB

Cite this

@article{bb5ec6cd3f2343f6b69cdf6e6d3e57b0,

title = "Machine Learning Based Physical Layer Security for Detecting Active Eavesdropping Attacks",

abstract = "This letter explores machine learning for enhancing physical layer security in a wireless system with an access point, legitimate users, and an active eavesdropper. During uplink training, the eavesdropper mimics pilot signals to compromise communication. We propose a framework to extract statistical features from wireless signals and build physical layer datasets. A one-class Support Vector Machine (OC-SVM) is used to detect such active eavesdropping attacks. Additionally, we introduce a twin-class SVM (TC-SVM) model to evaluate and compare detection performance. Simulation results demonstrate that our proposed approach with OC-SVM achieves a detection accuracy of 99.78\%, performing favorably compared to the TC-SVM model and other prior methods.",

keywords = "Machine learning, physical layer security, SVM",

author = "Cheng Yin and Pei Xiao and Vishal Sharma and Zheng Chu and Emiliano Garcia-Palacios",

note = "Publisher Copyright: {\textcopyright} 1997-2012 IEEE.",

year = "2025",

month = aug,

day = "31",

doi = "10.1109/LCOMM.2025.3582157",

language = "English",

volume = "29",

pages = "1978--1982",

journal = "IEEE Communications Letters",

issn = "1089-7798",

publisher = "IEEE",

number = "8",

}

TY - JOUR

T1 - Machine Learning Based Physical Layer Security for Detecting Active Eavesdropping Attacks

AU - Yin, Cheng

AU - Xiao, Pei

AU - Sharma, Vishal

AU - Chu, Zheng

AU - Garcia-Palacios, Emiliano

PY - 2025/8/31

Y1 - 2025/8/31

N2 - This letter explores machine learning for enhancing physical layer security in a wireless system with an access point, legitimate users, and an active eavesdropper. During uplink training, the eavesdropper mimics pilot signals to compromise communication. We propose a framework to extract statistical features from wireless signals and build physical layer datasets. A one-class Support Vector Machine (OC-SVM) is used to detect such active eavesdropping attacks. Additionally, we introduce a twin-class SVM (TC-SVM) model to evaluate and compare detection performance. Simulation results demonstrate that our proposed approach with OC-SVM achieves a detection accuracy of 99.78%, performing favorably compared to the TC-SVM model and other prior methods.

AB - This letter explores machine learning for enhancing physical layer security in a wireless system with an access point, legitimate users, and an active eavesdropper. During uplink training, the eavesdropper mimics pilot signals to compromise communication. We propose a framework to extract statistical features from wireless signals and build physical layer datasets. A one-class Support Vector Machine (OC-SVM) is used to detect such active eavesdropping attacks. Additionally, we introduce a twin-class SVM (TC-SVM) model to evaluate and compare detection performance. Simulation results demonstrate that our proposed approach with OC-SVM achieves a detection accuracy of 99.78%, performing favorably compared to the TC-SVM model and other prior methods.

KW - Machine learning

KW - physical layer security

KW - SVM

UR - https://ieeexplore.ieee.org/document/11045910/authors#authors

UR - https://pure.ulster.ac.uk/en/publications/bb5ec6cd-3f23-43f6-b69c-df6e6d3e57b0

UR - https://www.scopus.com/pages/publications/105009986030

U2 - 10.1109/LCOMM.2025.3582157

DO - 10.1109/LCOMM.2025.3582157

M3 - Article

SN - 1089-7798

VL - 29

SP - 1978

EP - 1982

JO - IEEE Communications Letters

JF - IEEE Communications Letters

IS - 8

ER -

Machine Learning Based Physical Layer Security for Detecting Active Eavesdropping Attacks

Abstract

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this