TY - JOUR
T1 - Transmit antenna selection in MIMO wiretap channels
T2 - A machine learning approach
AU - He, Dongxuan
AU - Liu, Chenxi
AU - Quek, Tony Q.S.
AU - Wang, Hua
N1 - Funding Information:
Manuscript received November 7, 2017; revised January 3, 2018; accepted February 8, 2018. Date of publication February 14, 2018; date of current version August 21, 2018. This work was supported in part by the China Scholarship Council (2017) under Grant 3109, and in part by the National Natural Science Foundation of China under Grant 61471037 and Grant 61201181. The associate editor coordinating the review of this paper and approving it for publication was P. P. Markopoulos. (Corresponding author: Chenxi Liu.) D. He and H. Wang are with the School of Information and Electronics, Beijing Institute of Technology, Beijing 100081, China (e-mail: hdxbit@bit.edu.cn; wanghua@bit.edu.cn).
Publisher Copyright:
© 2012 IEEE.
PY - 2018/8
Y1 - 2018/8
N2 - In this letter, we exploit the potential benefits of machine learning in enhancing physical layer security in multi-input multi-output multi-antenna-eavesdropper wiretap channels. To this end, we focus on the scenario where the source adopts transmit antenna selection (TAS) as the transmission strategy. We assume that the channel state information (CSI) of the legitimate receiver is available to the source, while the CSI of the eavesdropper can be either known or not known at the source. By modeling the problem of TAS as a multiclass classification problem, we propose two machine learning-based schemes, namely, the support vector machine-based scheme and the naive-Bayes-based scheme, to select the optimal antenna that maximizes the secrecy performance of the considered system. Compared to the conventional TAS scheme, we show that our proposed schemes can achieve almost the same secrecy performance with relatively small feedback overhead. The work presented here provides insights into the design of new machine learning-based secure transmission schemes.
AB - In this letter, we exploit the potential benefits of machine learning in enhancing physical layer security in multi-input multi-output multi-antenna-eavesdropper wiretap channels. To this end, we focus on the scenario where the source adopts transmit antenna selection (TAS) as the transmission strategy. We assume that the channel state information (CSI) of the legitimate receiver is available to the source, while the CSI of the eavesdropper can be either known or not known at the source. By modeling the problem of TAS as a multiclass classification problem, we propose two machine learning-based schemes, namely, the support vector machine-based scheme and the naive-Bayes-based scheme, to select the optimal antenna that maximizes the secrecy performance of the considered system. Compared to the conventional TAS scheme, we show that our proposed schemes can achieve almost the same secrecy performance with relatively small feedback overhead. The work presented here provides insights into the design of new machine learning-based secure transmission schemes.
UR - http://www.scopus.com/inward/record.url?scp=85042098129&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85042098129&partnerID=8YFLogxK
U2 - 10.1109/LWC.2018.2805902
DO - 10.1109/LWC.2018.2805902
M3 - Article
AN - SCOPUS:85042098129
VL - 7
SP - 634
EP - 637
JO - IEEE Wireless Communications Letters
JF - IEEE Wireless Communications Letters
SN - 2162-2337
IS - 4
M1 - 8291154
ER -