Short Blocklength Secret Coding via Helper-Assisted Learning over the Wiretap Channel

Consider the Gaussian wiretap channel, where a legitimate transmitter wishes to send a confidential message to a legitimate receiver in the presence of an eavesdropper. Unfortunately, in this setting, it is well known that if the eavesdropper experiences less channel noise than the legitimate receiver, then it is impossible for the transmitter to achieve positive secrecy rates. A known solution to this issue consists in involving a second transmitter, referred to as a helper, to help the first transmitter to achieve security. While such a solution has been studied for the asymptotic blocklength regime and via non-constructive coding schemes, in this paper, for the first time, we design explicit and short blocklength codes using deep learning and cryptographic tools to demonstrate the benefit and practicality of cooperation between two transmitters over the wiretap channel. Specifically, our proposed codes show strict improvement in terms of information leakage compared to existing point-to-point codes that do not consider a helper, even when the transmitter has adverse channel conditions, in the sense that the eavesdropper experiences less channel noise than the legitimate receiver. Our code design approach relies on a reliability layer, implemented with an autoencoder architecture inspired by the successive interference cancellation method developed for broadcast channels, and a security layer implemented with universal hash functions.