Q-Learning Based Physical-Layer Secure Game Against Multiagent Attacks
In this paper, we consider a Q-learning-based power allocation strategy for a secure physical-layer system under dynamic radio environments. In such a system, the transmitter sends the information to the receiver threatened by M(M ≥ 2) intelligent attackers which have several attack modes...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2019-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8686092/ |
id |
doaj-982358d88737450fa671d9f5b485b866 |
---|---|
record_format |
Article |
spelling |
doaj-982358d88737450fa671d9f5b485b8662021-03-29T22:20:22ZengIEEEIEEE Access2169-35362019-01-017492124922210.1109/ACCESS.2019.29102728686092Q-Learning Based Physical-Layer Secure Game Against Multiagent AttacksYan Xu0https://orcid.org/0000-0002-7895-6534Junjuan Xia1https://orcid.org/0000-0003-2787-6582Huijun Wu2Liseng Fan3School of Computer Science, Guangzhou University, Guangzhou, ChinaSchool of Computer Science, Guangzhou University, Guangzhou, ChinaSchool of Civil Engineering, Guangzhou University, Guangzhou, ChinaSchool of Computer Science, Guangzhou University, Guangzhou, ChinaIn this paper, we consider a Q-learning-based power allocation strategy for a secure physical-layer system under dynamic radio environments. In such a system, the transmitter sends the information to the receiver threatened by M(M ≥ 2) intelligent attackers which have several attack modes and will bring out the severe issue of information security. To safeguard the system security, we formulate the insecure problem as a stochastic game which consists of M+1 players: the transmitter which can flexibly choose its transmit power, and M smart attackers that can determine their attack types. Then, the Nash equilibria (NEs) of the physical-layer secure game are derived, and their existence conditions are taken into account. The simulation results show that the proposed power allocation strategy in the stochastic game can efficiently suppress the attack rate of smart attackers even if there exist multiple smart attackers.https://ieeexplore.ieee.org/document/8686092/Q-learningpower allocationsmart attacksstochastic game |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yan Xu Junjuan Xia Huijun Wu Liseng Fan |
spellingShingle |
Yan Xu Junjuan Xia Huijun Wu Liseng Fan Q-Learning Based Physical-Layer Secure Game Against Multiagent Attacks IEEE Access Q-learning power allocation smart attacks stochastic game |
author_facet |
Yan Xu Junjuan Xia Huijun Wu Liseng Fan |
author_sort |
Yan Xu |
title |
Q-Learning Based Physical-Layer Secure Game Against Multiagent Attacks |
title_short |
Q-Learning Based Physical-Layer Secure Game Against Multiagent Attacks |
title_full |
Q-Learning Based Physical-Layer Secure Game Against Multiagent Attacks |
title_fullStr |
Q-Learning Based Physical-Layer Secure Game Against Multiagent Attacks |
title_full_unstemmed |
Q-Learning Based Physical-Layer Secure Game Against Multiagent Attacks |
title_sort |
q-learning based physical-layer secure game against multiagent attacks |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2019-01-01 |
description |
In this paper, we consider a Q-learning-based power allocation strategy for a secure physical-layer system under dynamic radio environments. In such a system, the transmitter sends the information to the receiver threatened by M(M ≥ 2) intelligent attackers which have several attack modes and will bring out the severe issue of information security. To safeguard the system security, we formulate the insecure problem as a stochastic game which consists of M+1 players: the transmitter which can flexibly choose its transmit power, and M smart attackers that can determine their attack types. Then, the Nash equilibria (NEs) of the physical-layer secure game are derived, and their existence conditions are taken into account. The simulation results show that the proposed power allocation strategy in the stochastic game can efficiently suppress the attack rate of smart attackers even if there exist multiple smart attackers. |
topic |
Q-learning power allocation smart attacks stochastic game |
url |
https://ieeexplore.ieee.org/document/8686092/ |
work_keys_str_mv |
AT yanxu qlearningbasedphysicallayersecuregameagainstmultiagentattacks AT junjuanxia qlearningbasedphysicallayersecuregameagainstmultiagentattacks AT huijunwu qlearningbasedphysicallayersecuregameagainstmultiagentattacks AT lisengfan qlearningbasedphysicallayersecuregameagainstmultiagentattacks |
_version_ |
1724191873469251584 |