Jamming for Secrecy: Reinforcement Learning Based Anti-Eavesdropping Visible Light Communication

Due to the broadcast nature of visible light communication (VLC), the secrecy protection is a crucial issue. In this paper, aiming at the communication scenario of a point-to-point VLC transmission link, an anti-eavesdropping model utilizing friendly jamming is constructed, which is composed of a light-emitting diode (LED) transmitter, a legitimate receiver equipped with a photodiode (PD), and a potential eavesdropper trying to obtain the undisclosed information transmitted. In addition, the system is equipped with a friendly jammer composed of multiple LEDs. A friendly jamming scheme based on reinforcement learning (RL) is proposed, which adopts different friendly jamming actions with the dynamic change of the environment. The simulation results show that compared with the benchmark state-of-the-art method, the proposed scheme can significantly reduce the bit error rate (BER) of the legitimate receiver and improve the overall performance of the anti-eavesdropping VLC system.