Secret Key Generation Driven by Attention-Based Convolutional Autoencoder and Quantile Quantization for IoT Security in 5G and Beyond

Physical-layer secret key generation (PSKG) has emerged as a promising technique for enhancing wireless security in Internet of Things (IoT) networks by exploiting the reciprocity of uplink and downlink channels. However, in time-division duplex (TDD) systems, hardware impairments and channel noise...

Full description

Saved in:
Bibliographic Details
Main Authors: Anas Alashqar, Ehsan Olyaei Torshizi, Raed Mesleh, Werner Henkel
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11086605/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850075731751600128
author Anas Alashqar
Ehsan Olyaei Torshizi
Raed Mesleh
Werner Henkel
author_facet Anas Alashqar
Ehsan Olyaei Torshizi
Raed Mesleh
Werner Henkel
author_sort Anas Alashqar
collection DOAJ
description Physical-layer secret key generation (PSKG) has emerged as a promising technique for enhancing wireless security in Internet of Things (IoT) networks by exploiting the reciprocity of uplink and downlink channels. However, in time-division duplex (TDD) systems, hardware impairments and channel noise disrupt channel reciprocity, degrading key generation performance. To overcome these challenges, this paper introduces a deep learning–enhanced PSKG framework that effectively mitigates channel discrepancies and improves key generation reliability under imperfect channel state information (CSI). Specifically, a two-dimensional convolutional neural network–based autoencoder (2D CNN–AE) with a spatial self-attention (SSA) mechanism is developed to efficiently extract and learn channel reciprocity features in time-division duplex (TDD)-based fifth-generation (5G) networks. Additionally, a quantile-based quantization scheme is proposed to enhance key randomness and entropy, thereby strengthening security and resilience against potential threats. To facilitate comprehensive performance evaluation, a wiretap channel dataset is generated in accordance with 5G standards, encompassing diverse propagation conditions and including both legitimate users and an eavesdropper. Extensive simulation results demonstrate that the proposed 2D CNN–AE–SSA-based PSKG framework significantly reduces the key disagreement ratio (KDR), enhances key randomness, and maintains low computational complexity. These findings establish the proposed method as a robust and practical solution for securing wireless communications in resource-constrained IoT environments.
format Article
id doaj-art-0b76fcf31d6f473b829a5031cea1e7e5
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-0b76fcf31d6f473b829a5031cea1e7e52025-08-20T02:46:13ZengIEEEIEEE Access2169-35362025-01-011313174413175610.1109/ACCESS.2025.359092611086605Secret Key Generation Driven by Attention-Based Convolutional Autoencoder and Quantile Quantization for IoT Security in 5G and BeyondAnas Alashqar0https://orcid.org/0000-0001-8107-5132Ehsan Olyaei Torshizi1https://orcid.org/0000-0003-0724-0907Raed Mesleh2https://orcid.org/0000-0001-6838-2816Werner Henkel3https://orcid.org/0000-0003-4959-8560School of Computer Science and Engineering, Constructor University, Bremen, GermanySchool of Computer Science and Engineering, Constructor University, Bremen, GermanySchool of Electrical Engineering and Information Technology, German Jordanian University, Amman, JordanSchool of Computer Science and Engineering, Constructor University, Bremen, GermanyPhysical-layer secret key generation (PSKG) has emerged as a promising technique for enhancing wireless security in Internet of Things (IoT) networks by exploiting the reciprocity of uplink and downlink channels. However, in time-division duplex (TDD) systems, hardware impairments and channel noise disrupt channel reciprocity, degrading key generation performance. To overcome these challenges, this paper introduces a deep learning–enhanced PSKG framework that effectively mitigates channel discrepancies and improves key generation reliability under imperfect channel state information (CSI). Specifically, a two-dimensional convolutional neural network–based autoencoder (2D CNN–AE) with a spatial self-attention (SSA) mechanism is developed to efficiently extract and learn channel reciprocity features in time-division duplex (TDD)-based fifth-generation (5G) networks. Additionally, a quantile-based quantization scheme is proposed to enhance key randomness and entropy, thereby strengthening security and resilience against potential threats. To facilitate comprehensive performance evaluation, a wiretap channel dataset is generated in accordance with 5G standards, encompassing diverse propagation conditions and including both legitimate users and an eavesdropper. Extensive simulation results demonstrate that the proposed 2D CNN–AE–SSA-based PSKG framework significantly reduces the key disagreement ratio (KDR), enhances key randomness, and maintains low computational complexity. These findings establish the proposed method as a robust and practical solution for securing wireless communications in resource-constrained IoT environments.https://ieeexplore.ieee.org/document/11086605/Autoencoderself-attentionCNNdeep learningIoT securitychannel reciprocity
spellingShingle Anas Alashqar
Ehsan Olyaei Torshizi
Raed Mesleh
Werner Henkel
Secret Key Generation Driven by Attention-Based Convolutional Autoencoder and Quantile Quantization for IoT Security in 5G and Beyond
IEEE Access
Autoencoder
self-attention
CNN
deep learning
IoT security
channel reciprocity
title Secret Key Generation Driven by Attention-Based Convolutional Autoencoder and Quantile Quantization for IoT Security in 5G and Beyond
title_full Secret Key Generation Driven by Attention-Based Convolutional Autoencoder and Quantile Quantization for IoT Security in 5G and Beyond
title_fullStr Secret Key Generation Driven by Attention-Based Convolutional Autoencoder and Quantile Quantization for IoT Security in 5G and Beyond
title_full_unstemmed Secret Key Generation Driven by Attention-Based Convolutional Autoencoder and Quantile Quantization for IoT Security in 5G and Beyond
title_short Secret Key Generation Driven by Attention-Based Convolutional Autoencoder and Quantile Quantization for IoT Security in 5G and Beyond
title_sort secret key generation driven by attention based convolutional autoencoder and quantile quantization for iot security in 5g and beyond
topic Autoencoder
self-attention
CNN
deep learning
IoT security
channel reciprocity
url https://ieeexplore.ieee.org/document/11086605/
work_keys_str_mv AT anasalashqar secretkeygenerationdrivenbyattentionbasedconvolutionalautoencoderandquantilequantizationforiotsecurityin5gandbeyond
AT ehsanolyaeitorshizi secretkeygenerationdrivenbyattentionbasedconvolutionalautoencoderandquantilequantizationforiotsecurityin5gandbeyond
AT raedmesleh secretkeygenerationdrivenbyattentionbasedconvolutionalautoencoderandquantilequantizationforiotsecurityin5gandbeyond
AT wernerhenkel secretkeygenerationdrivenbyattentionbasedconvolutionalautoencoderandquantilequantizationforiotsecurityin5gandbeyond