Reinforcement Learning-Based Intelligent Reflecting Surface Assisted Communications Against Smart Attackers

Li, Baogang; Shi, Tai; Zhao, Wei; Wang, Ning

doi:10.1109/tcomm.2022.3178755

Cited by 11 publications

(5 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [21], the authors propose a RIS-assisted key generation scheme by intervening in the propagation in harsh environments. In [22], the authors exploit the noncooperative game to model the interaction between a RISassisted legitimate user and a smart attacker with learningbased security solutions.…”

Section: Related Workmentioning

confidence: 99%

“…by comparing the elements in ∆H JRk and ∆ Hk , with Υ JRk similarly introduced. For the inequalities in ( 20), (22), and (24) with quadratic forms on the left-hand side, we can adopt general S-procedure [36] to derive the following inequality in (25), where {η 1,k } k∈K and {η 2,k } k∈K are the introduced non-negative variables associated with the condition in ( 22) and ( 24) in the general S-procedure, respectively.…”

Section: By Invoking the Equality Trmentioning

confidence: 99%

See 1 more Smart Citation

Robust Secrecy via Aerial Reflection and Jamming: Joint Optimization of Deployment and Transmission

Tang¹,

He²,

Dong³

et al. 2023

Preprint

View full text Add to dashboard Cite

Reconfigurable intelligent surfaces (RISs) are recognized with great potential to strengthen wireless security, yet the performance gain largely depends on the deployment location of RISs in the network topology. In this paper, we consider the anti-eavesdropping communication established through a RIS at a fixed location, as well as an aerial platform mounting another RIS and a friendly jammer to further improve the secrecy. The aerial RIS helps enhance the legitimate signal and the aerial cooperative jamming is strengthened through the fixed RIS. The security gain with aerial reflection and jamming is further improved with the optimized deployment of the aerial platform. We particularly consider the imperfect channel state information issue and address the worst-case secrecy for robust performance. The formulated robust secrecy rate maximization problem is decomposed into two layers, where the inner layer solves for reflection and jamming with robust optimization, and the outer layer tackles the aerial deployment through deep reinforcement learning. Simulation results show the deployment under different network topologies and demonstrate the performance superiority of our proposal in terms of the worst-case security provisioning as compared with the baselines.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: By Invoking the Equality Trmentioning

confidence: 99%

Robust Secrecy via Aerial Reflection and Jamming: Joint Optimization of Deployment and Transmission

Tang¹,

He²,

Dong³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Artificial Intelligence (AI) has introduced a new way to solve PLS problems through RL. Recent studies in [ 20 , 21 ] have considered PLS problems concerning smart attackers conducting jamming, eavesdropping, and spoofing attacks. For instance, prospect theory (PT) in an unmanned aerial vehicle (UAV) transmission system is investigated in [ 20 ], where the attacker is considered to be selfish and subjective.…”

Section: Related Workmentioning

confidence: 99%

“…To enhance the secrecy performance and the utility of the legitimate UAV, a power allocation approach utilizing deep Q-networks (DQN) is put forth to determine the optimal policy, in cases where the attack and channel models are unknown. RL techniques are studied in [ 21 ] to configure IRS beamforming design. The authors first establish the interaction between the base station (BS) and the smart attacker as a non-cooperative game and derive the Nash equilibrium of the game.…”

Section: Related Workmentioning

confidence: 99%

Learning-Based IRS-Assisted Secure Transmission for Mine IoTs

Min

Xiao

Zhang

et al. 2023

Sensors

View full text Add to dashboard Cite

Mine Internet of Things (MIoT) devices in intelligent mines often face substantial signal attenuation due to challenging operating conditions. The openness of wireless communication also makes it susceptible to smart attackers, such as active eavesdroppers. The attackers can disrupt equipment operations, compromise production safety, and exfiltrate sensitive environmental data. To address these challenges, we propose an intelligent reflecting surface (IRS)-assisted secure transmission system for an MIoT device which enhances the security and reliability of wireless communication in challenging mining environments. We develop a joint optimization problem for the IRS phase shifts and transmit power, with the goal of enhancing legitimate transmission while suppressing eavesdropping. To accommodate time-varying channel conditions, we propose a reinforcement learning (RL)-based IRS-assisted secure transmission scheme that enables MIoT device to optimize both the IRS reflecting coefficients and transmit power for optimal transmission policy in dynamic environments. We adopt the deep deterministic policy gradient (DDPG) algorithm to explore the optimal transmission policy in continuous space. This can reduce the discretization error caused by traditional RL methods. The simulation results indicate that our proposed scheme achieves superior system utility compared with both the IRS-free (IF) scheme and the IRS randomly configured (IRC) scheme. These results demonstrate the effectiveness and practical relevance of our contributions, proving that implementing IRS in MIoT wireless communication can enhance safety, security, and efficiency in the mining industry.

show abstract

“…The findings indicated that the DQN algorithm was more suitable than the Q-learning algorithm for systems with huge action and state spaces. In [294], the security of RIS-enabled wireless networks was investigated in the presence of intelligent attackers. DQN was introduced to enable adaptive modulation of BS and RIS reflection beamforming.…”

Section: A Deep Reinforcement Learningmentioning

confidence: 99%

Relay Selection for Improving Physical Layer Security in D2D Underlay Communications

2022

View full text Add to dashboard Cite

This paper investigates the physical layer security of inband underlay Device-to-Device (D2D) communication, where the direct link between D2D users is not available. In this respect, optimal relay and suboptimal relay selections are utilized to secure the D2D transmission. The eavesdropper uses either maximal-ratio combining or selection combining to increase the wiretapped signals. The D2D secrecy performance analysis is performed regarding the secrecy outage probability (SOP) and the probability of non-zero secrecy capacity, and closed-form expressions are provided for both relay selection approaches and verified using Monte-Carlo simulation. From the numerical results, it is shown that increasing the number of D2D relays enhances the secrecy performance of D2D communications. Moreover, the exact asymptotic analysis of the SOP is provided. It turns out that the diversity order of both relay selection approaches is the same.INDEX TERMS Physical layer security, D2D communications, secrecy outage probability, optimal and suboptimal relay selection, maximal-ratio combining, and selection combining., 1

show abstract

Reinforcement Learning-Based Intelligent Reflecting Surface Assisted Communications Against Smart Attackers

Cited by 11 publications

References 22 publications

Robust Secrecy via Aerial Reflection and Jamming: Joint Optimization of Deployment and Transmission

Robust Secrecy via Aerial Reflection and Jamming: Joint Optimization of Deployment and Transmission

Learning-Based IRS-Assisted Secure Transmission for Mine IoTs

Relay Selection for Improving Physical Layer Security in D2D Underlay Communications

Contact Info

Product

Resources

About