Physical Layer Security: Detection of Active Eavesdropping Attacks by Support Vector Machines
Physical Layer Security: Detection of Active Eavesdropping Attacks by Support Vector Machines
This article presents a framework for converting wireless signals into structured datasets, which can be fed into machine learning algorithms for the detection of active eavesdropping attacks at the physical layer. More specifically, a wireless communication system, which consists of an access point (AP), K legitimate users and an active eavesdropper, is considered. To detect the eavesdropper who breaks into the system during the authentication phase, we first build structured datasets based on different features and then apply sophisticated support vector machine (SVM) classifiers to those structured datasets. To be more specific, we first process the signals received by the AP and then define a pair of statistical features based on the post-processing of the signals. By arranging for the AP to simulate the entire process of transmission and the process of constructing features, we form the so-called artificial training data (ATD). By training SVM classifiers on the ATD, we classify the received signals associated with eavesdropping attacks and non-attacks, thereby detecting the presence of the eavesdropper. Two SVM classifiers are considered, including a classic twin-class SVM (TC-SVM) and a single-class SVM (SC-SVM). While the TC-SVM is preferred in the case of having perfect channel state information (CSI) of all channels, the SC-SVM is preferred in the realistic scenario when we have only the CSI of legitimate users. We also evaluate the accuracy of the trained models depending on the choice of kernel functions, the choice of features and on the eavesdropper's power. Our numerical results show that careful parameter-tuning is required for exceeding an eavesdropper detection probability of 95%.
Communication system security, Eavesdropping, Kernel, Physical layer security, Support vector machines, Training, Training data, Wireless communication, active eavesdropping, machine learning, single-class SVM, support vector machine (SVM)
31595-31607
Hoang, Minh Tiep
79ed4c0b-02ee-420a-a4cf-eeb0c2715d76
Duong, Trung Q.
406d80a2-b57f-4955-85aa-c5bc5a236b04
Tuan, Hoang Duong
423ee18d-ebc7-44d9-9264-3819b63779eb
Lambotharan, Sangarapillai
9839317e-0bf4-4d7c-8722-87d3ec9086de
Hanzo, Lajos
66e7266f-3066-4fc0-8391-e000acce71a1
2021
Hoang, Minh Tiep
79ed4c0b-02ee-420a-a4cf-eeb0c2715d76
Duong, Trung Q.
406d80a2-b57f-4955-85aa-c5bc5a236b04
Tuan, Hoang Duong
423ee18d-ebc7-44d9-9264-3819b63779eb
Lambotharan, Sangarapillai
9839317e-0bf4-4d7c-8722-87d3ec9086de
Hanzo, Lajos
66e7266f-3066-4fc0-8391-e000acce71a1
Hoang, Minh Tiep, Duong, Trung Q., Tuan, Hoang Duong, Lambotharan, Sangarapillai and Hanzo, Lajos
(2021)
Physical Layer Security: Detection of Active Eavesdropping Attacks by Support Vector Machines.
IEEE Access, 9, , [3059648].
(doi:10.1109/ACCESS.2021.3059648).
Abstract
This article presents a framework for converting wireless signals into structured datasets, which can be fed into machine learning algorithms for the detection of active eavesdropping attacks at the physical layer. More specifically, a wireless communication system, which consists of an access point (AP), K legitimate users and an active eavesdropper, is considered. To detect the eavesdropper who breaks into the system during the authentication phase, we first build structured datasets based on different features and then apply sophisticated support vector machine (SVM) classifiers to those structured datasets. To be more specific, we first process the signals received by the AP and then define a pair of statistical features based on the post-processing of the signals. By arranging for the AP to simulate the entire process of transmission and the process of constructing features, we form the so-called artificial training data (ATD). By training SVM classifiers on the ATD, we classify the received signals associated with eavesdropping attacks and non-attacks, thereby detecting the presence of the eavesdropper. Two SVM classifiers are considered, including a classic twin-class SVM (TC-SVM) and a single-class SVM (SC-SVM). While the TC-SVM is preferred in the case of having perfect channel state information (CSI) of all channels, the SC-SVM is preferred in the realistic scenario when we have only the CSI of legitimate users. We also evaluate the accuracy of the trained models depending on the choice of kernel functions, the choice of features and on the eavesdropper's power. Our numerical results show that careful parameter-tuning is required for exceeding an eavesdropper detection probability of 95%.
More information
Accepted/In Press date: 2021
e-pub ahead of print date: 16 February 2021
Published date: 2021
Additional Information:
Funding Information:
The work of Lajos Hanzo was supported in part by the Engineering and Physical Sciences Research Council under Project EP/P034284/1 and Project EP/P003990/1 (COALESCE) and in part by the European Research Council's Advanced Fellow Grant QuantCom under Grant 789028.
Publisher Copyright:
© 2021 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.
Keywords:
Communication system security, Eavesdropping, Kernel, Physical layer security, Support vector machines, Training, Training data, Wireless communication, active eavesdropping, machine learning, single-class SVM, support vector machine (SVM)
Identifiers
Local EPrints ID: 447283
URI: http://eprints.soton.ac.uk/id/eprint/447283
ISSN: 2169-3536
PURE UUID: 60d0c3ed-313f-44af-b70d-c23fb1fd1bef
Catalogue record
Date deposited: 08 Mar 2021 17:32
Last modified: 06 Jun 2024 01:32
Export record
Altmetrics
Contributors
Author:
Minh Tiep Hoang
Author:
Trung Q. Duong
Author:
Hoang Duong Tuan
Author:
Sangarapillai Lambotharan
Author:
Lajos Hanzo
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics