Concept Drift Aware Wireless Key Generation in Dynamic LiFi Networks

This paper studies the generation of cryptographic keys from wireless channels in light-fidelity (LiFi) networks. Unlike existing studies, we account for several practical considerations (a) realistic indoor multi-user mobility scenarios, (b) non-ideal channel reciprocity given the unique characteri...

Full description

Saved in:
Bibliographic Details
Main Authors: Elmahedi Mahalal, Eslam Hasan, Muhammad Ismail, Zi-Yang Wu, Mostafa M. Fouda, Zubair Md Fadlullah, Nei Kato
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Open Journal of the Communications Society
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10818749/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849700899561144320
author Elmahedi Mahalal
Eslam Hasan
Muhammad Ismail
Zi-Yang Wu
Mostafa M. Fouda
Zubair Md Fadlullah
Nei Kato
author_facet Elmahedi Mahalal
Eslam Hasan
Muhammad Ismail
Zi-Yang Wu
Mostafa M. Fouda
Zubair Md Fadlullah
Nei Kato
author_sort Elmahedi Mahalal
collection DOAJ
description This paper studies the generation of cryptographic keys from wireless channels in light-fidelity (LiFi) networks. Unlike existing studies, we account for several practical considerations (a) realistic indoor multi-user mobility scenarios, (b) non-ideal channel reciprocity given the unique characteristics of the downlink visible light (VL) and uplink infrared (IR) channels, (c) different room occupancy levels, (d) different room layouts, and (e) different receivers’ field-of-view (FoV). Since general channel models in dynamic LiFi networks are inaccurate, we propose a novel deep learning-based framework to generate secret keys with minimal key disagreement rate (KDR) and maximal key generation rate (KGR). However, we find that wireless channels in LiFi networks exhibit different statistical behaviors under various conditions, leading to concept drift in the deep learning model. As a result, key generation suffers from (a) a deterioration in KDR and KGR up to 29% and 38%, respectively, and (b) failing the NIST randomness test. To enable a concept drift aware framework, we propose an adaptive learning strategy using the similarity of channel probability density functions and the mix-of-experts ensemble method. Results show our adaptive learning strategy can achieve stable performance that passes the NIST randomness test and achieves 8% KDR and 89 bits/s KGR for a case of study with 60° FoV.
format Article
id doaj-art-9c04eb37d0ad49bebb206764cb9b5bd9
institution DOAJ
issn 2644-125X
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Open Journal of the Communications Society
spelling doaj-art-9c04eb37d0ad49bebb206764cb9b5bd92025-08-20T03:18:07ZengIEEEIEEE Open Journal of the Communications Society2644-125X2025-01-01674275810.1109/OJCOMS.2024.352449710818749Concept Drift Aware Wireless Key Generation in Dynamic LiFi NetworksElmahedi Mahalal0https://orcid.org/0000-0001-7248-1470Eslam Hasan1https://orcid.org/0000-0001-7385-2632Muhammad Ismail2https://orcid.org/0000-0002-8051-9747Zi-Yang Wu3https://orcid.org/0000-0002-5334-3686Mostafa M. Fouda4https://orcid.org/0000-0003-1790-8640Zubair Md Fadlullah5https://orcid.org/0000-0002-4785-2425Nei Kato6https://orcid.org/0000-0001-8769-302XDepartment of Electrical, Computer Engineering and Computer Science, University of New Haven, West Haven, CT, USADepartment of Computer Science, Tennessee Tech University, Cookeville, TN, USADepartment of Computer Science, Tennessee Tech University, Cookeville, TN, USACollege of Information Science and Engineering, Northeastern University, Shenyang, ChinaDepartment of Electrical and Computer Engineering, Idaho State University, Pocatello, ID, USADepartment of Computer Science, Western University, London, ON, CanadaGraduate School of Information Sciences, Tohoku University, Sendai, JapanThis paper studies the generation of cryptographic keys from wireless channels in light-fidelity (LiFi) networks. Unlike existing studies, we account for several practical considerations (a) realistic indoor multi-user mobility scenarios, (b) non-ideal channel reciprocity given the unique characteristics of the downlink visible light (VL) and uplink infrared (IR) channels, (c) different room occupancy levels, (d) different room layouts, and (e) different receivers’ field-of-view (FoV). Since general channel models in dynamic LiFi networks are inaccurate, we propose a novel deep learning-based framework to generate secret keys with minimal key disagreement rate (KDR) and maximal key generation rate (KGR). However, we find that wireless channels in LiFi networks exhibit different statistical behaviors under various conditions, leading to concept drift in the deep learning model. As a result, key generation suffers from (a) a deterioration in KDR and KGR up to 29% and 38%, respectively, and (b) failing the NIST randomness test. To enable a concept drift aware framework, we propose an adaptive learning strategy using the similarity of channel probability density functions and the mix-of-experts ensemble method. Results show our adaptive learning strategy can achieve stable performance that passes the NIST randomness test and achieves 8% KDR and 89 bits/s KGR for a case of study with 60° FoV.https://ieeexplore.ieee.org/document/10818749/Concept driftchannel reciprocitydeep learninginfrared channelkey disagreement rate (KDR)key generation rate (KGR)
spellingShingle Elmahedi Mahalal
Eslam Hasan
Muhammad Ismail
Zi-Yang Wu
Mostafa M. Fouda
Zubair Md Fadlullah
Nei Kato
Concept Drift Aware Wireless Key Generation in Dynamic LiFi Networks
IEEE Open Journal of the Communications Society
Concept drift
channel reciprocity
deep learning
infrared channel
key disagreement rate (KDR)
key generation rate (KGR)
title Concept Drift Aware Wireless Key Generation in Dynamic LiFi Networks
title_full Concept Drift Aware Wireless Key Generation in Dynamic LiFi Networks
title_fullStr Concept Drift Aware Wireless Key Generation in Dynamic LiFi Networks
title_full_unstemmed Concept Drift Aware Wireless Key Generation in Dynamic LiFi Networks
title_short Concept Drift Aware Wireless Key Generation in Dynamic LiFi Networks
title_sort concept drift aware wireless key generation in dynamic lifi networks
topic Concept drift
channel reciprocity
deep learning
infrared channel
key disagreement rate (KDR)
key generation rate (KGR)
url https://ieeexplore.ieee.org/document/10818749/
work_keys_str_mv AT elmahedimahalal conceptdriftawarewirelesskeygenerationindynamiclifinetworks
AT eslamhasan conceptdriftawarewirelesskeygenerationindynamiclifinetworks
AT muhammadismail conceptdriftawarewirelesskeygenerationindynamiclifinetworks
AT ziyangwu conceptdriftawarewirelesskeygenerationindynamiclifinetworks
AT mostafamfouda conceptdriftawarewirelesskeygenerationindynamiclifinetworks
AT zubairmdfadlullah conceptdriftawarewirelesskeygenerationindynamiclifinetworks
AT neikato conceptdriftawarewirelesskeygenerationindynamiclifinetworks