DeepFake: Deep Dueling-based Deception Strategy to Defeat Reactive Jammers

View on arXiv ← Back to list

Authors: Nguyen Van Huynh, Dinh Thai Hoang, Diep N. Nguyen, Eryk Dutkiewicz

Published: 2020-05-13 00:37:43+00:00

AI Summary

This paper proposes DeepFake, a deep reinforcement learning-based deception strategy to combat reactive jamming attacks. The approach uses a deep dueling neural network to learn an optimal policy for the transmitter, enabling it to lure the jammer with fake signals and then utilize the resulting jamming signals for data transmission or energy harvesting.

Abstract

In this paper, we introduce DeepFake, a novel deep reinforcement learning-based deception strategy to deal with reactive jamming attacks. In particular, for a smart and reactive jamming attack, the jammer is able to sense the channel and attack the channel if it detects communications from the legitimate transmitter. To deal with such attacks, we propose an intelligent deception strategy which allows the legitimate transmitter to transmit fake signals to attract the jammer. Then, if the jammer attacks the channel, the transmitter can leverage the strong jamming signals to transmit data by using ambient backscatter communication technology or harvest energy from the strong jamming signals for future use. By doing so, we can not only undermine the attack ability of the jammer, but also utilize jamming signals to improve the system performance. To effectively learn from and adapt to the dynamic and uncertainty of jamming attacks, we develop a novel deep reinforcement learning algorithm using the deep dueling neural network architecture to obtain the optimal policy with thousand times faster than those of the conventional reinforcement algorithms. Extensive simulation results reveal that our proposed DeepFake framework is superior to other anti-jamming strategies in terms of throughput, packet loss, and learning rate.

Key findings

Simulation results demonstrate that DeepFake outperforms other anti-jamming strategies in throughput, packet loss, and learning rate. The approach effectively utilizes jamming signals, improving performance as jammer power increases. The deep dueling network achieves a significantly faster convergence rate compared to conventional reinforcement learning methods.

Approach

DeepFake employs a deep reinforcement learning algorithm with a deep dueling neural network architecture. The transmitter uses a two-decision epoch Markov Decision Process (MDP) to learn the optimal strategy for deceiving the jammer and leveraging jamming signals for energy harvesting or backscatter communication. This allows the system to adapt to the dynamic and uncertain nature of jamming attacks.

Datasets

UNKNOWN

Model(s)

Deep dueling neural network, Deep Q-learning

Author countries

Australia

← Previous