Dual MINE-based Neural Secure Communications under Gaussian Wiretap Channel

TL;DR

This paper introduces a dual MINE-based neural secure communication model that enhances security by relying solely on input-output samples of legitimate and eavesdropper channels, independent of the eavesdropper's decoding capabilities.

Contribution

It proposes a novel neural secure communication framework using dual mutual information neural estimation that does not depend on the eavesdropper's decoder outputs.

Findings

Model maintains security regardless of eavesdropper's decoding method

Security performance is robust under various eavesdropper strategies

Encoder training is independent of the eavesdropper's decoder

Abstract

Recently, some researches are devoted to the topic of end-to-end learning a physical layer secure communication system based on autoencoder under Gaussian wiretap channel. However, in those works, the reliability and security of the encoder model were learned through necessary decoding outputs of not only legitimate receiver but also the eavesdropper. In fact, the assumption of known eavesdropper's decoder or its output is not practical. To address this issue, in this paper we propose a dual mutual information neural estimation (MINE) based neural secure communications model. The security constraints of this method is constructed only with the input and output signal samples of the legal and eavesdropper channels and benefit that training the encoder is completely independent of the decoder. Moreover, since the design of secure coding does not rely on the eavesdropper's decoding results, the security performance would not be affected by the eavesdropper's decoding means. Numerical results show that the performance of our model is guaranteed whether the eavesdropper learns the decoder himself or uses the legal decoder.