Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Cooperative Jamming for Physical Layer Security Enhancement Using Deep Reinforcement Learning

Sayed Amir Hoseini, Faycal Bouhafs, Neda Aboutorab, Parastoo Sadeghi, Frank den Hartog

TL;DR

An optimization approach to achieve CFJ in large Wi-Fi networks by using a Reinforcement Learning Algorithm is proposed and results show that the optimization approach offers better secrecy results and becomes more effective as the network size and the density of Wi-Fi access points increase.

Abstract

Wireless data communications are always facing the risk of eavesdropping and interception. Conventional protection solutions which are based on encryption may not always be practical as is the case for wireless IoT networks or may soon become ineffective against quantum computers. In this regard, Physical Layer Security (PLS) presents a promising approach to secure wireless communications through the exploitation of the physical properties of the wireless channel. Cooperative Friendly Jamming (CFJ) is among the PLS techniques that have received attention in recent years. However, finding an optimal transmit power allocation that results in the highest secrecy is a complex problem that becomes more difficult to address as the size of the wireless network increases. In this paper, we propose an optimization approach to achieve CFJ in large Wi-Fi networks by using a Reinforcement Learning Algorithm. Obtained results show that our optimization approach offers better secrecy results and becomes more effective as the network size and the density of Wi-Fi access points increase.

Cooperative Jamming for Physical Layer Security Enhancement Using Deep Reinforcement Learning

TL;DR

An optimization approach to achieve CFJ in large Wi-Fi networks by using a Reinforcement Learning Algorithm is proposed and results show that the optimization approach offers better secrecy results and becomes more effective as the network size and the density of Wi-Fi access points increase.

Abstract

Wireless data communications are always facing the risk of eavesdropping and interception. Conventional protection solutions which are based on encryption may not always be practical as is the case for wireless IoT networks or may soon become ineffective against quantum computers. In this regard, Physical Layer Security (PLS) presents a promising approach to secure wireless communications through the exploitation of the physical properties of the wireless channel. Cooperative Friendly Jamming (CFJ) is among the PLS techniques that have received attention in recent years. However, finding an optimal transmit power allocation that results in the highest secrecy is a complex problem that becomes more difficult to address as the size of the wireless network increases. In this paper, we propose an optimization approach to achieve CFJ in large Wi-Fi networks by using a Reinforcement Learning Algorithm. Obtained results show that our optimization approach offers better secrecy results and becomes more effective as the network size and the density of Wi-Fi access points increase.
Paper Structure (7 sections, 8 equations, 3 figures)

This paper contains 7 sections, 8 equations, 3 figures.

Table of Contents

  1. Introduction
  2. Related Work
  3. System Model
  4. Proposed Friendly Jamming Formulation
  5. Proposed Reinforcement Learning Model
  6. Performance Evaluation
  7. Conclusions and Future Work

Figures (3)

  • Figure 1: In a cooperative wireless network, user$_1$ and user$_2$ receive downlink traffic from AP$_1$ and AP$_3$, respectively (shown by green dotted lines). However, Eve$_1$ and Eve$_2$ are eavesdropping on their traffic (indicated by red dotted lines). Additionally, AP$_2$ and AP$_4$ are idle and act as jammers. It is important to note that all APs and users communicate in the same frequency band. As a result, AP$_1$'s signal can also be considered as jamming signal for any eavesdropper wiretapping AP$_3$'s traffic, and AP$_2$'s signal can also be considered as jamming signal for any eavesdropper wiretapping AP$_1$'s traffic.
  • Figure 2: These figures display the locations of users, eavesdroppers, and APs in various scenarios. Scenarios 3, 4, 5, and 6 involve identical numbers and locations of users and eavesdroppers, with only new APs being introduced.
  • Figure 3: Results for different scenarios for 3 different implementations. Rl-based CFJ can generally outperform other implementations. Scenarios 3, 4, 5, and 6 involve identical numbers and locations of users and eavesdroppers, with only new APs being introduced. Therefore, secrecy can be improved by deploying more APs. Although scenario 5 is expected to perform as well as or better than scenario 4 for RL-based CFJ, the results show a slight downgrade. This is because the AP selection algorithm is run separately from power optimization and before it.