Secret Key Generation Scheme Based on Deep Learning in FDD MIMO Systems

Zheng WAN
Kaizhi HUANG
Lu CHEN

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E104-D    No.7    pp.1058-1062
Publication Date: 2021/07/01
Publicized: 2021/04/07
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2020EDL8145
Type of Manuscript: LETTER
Category: Artificial Intelligence, Data Mining
Keyword: 
physical layer security,  secret key generation,  deep learning,  FDD MIMO systems,  

Full Text: PDF>>
Buy this Article



Summary: 
In this paper, a deep learning-based secret key generation scheme is proposed for FDD multiple-input and multiple-output (MIMO) systems. We built an encoder-decoder based convolutional neural network to characterize the wireless environment to learn the mapping relationship between the uplink and downlink channel. The designed neural network can accurately predict the downlink channel state information based on the estimated uplink channel state information without any information feedback. Random secret keys can be generated from downlink channel responses predicted by the neural network. Simulation results show that deep learning based SKG scheme can achieve significant performance improvement in terms of the key agreement ratio and achievable secret key rate.