Helper-Assisted Coding for Gaussian Wiretap Channels: Deep Learning Meets PhySec

2025-12-01

IEEE Transactions on Communications

AI Summary

This work addresses the challenge of achieving positive secrecy rates in Gaussian wiretap channels when the eavesdropper’s channel is stronger than that of the legitimate receiver—a regime where conventional physical-layer security methods typically fail. The authors propose a cooperative two-transmitter scheme that integrates a reliability layer, implemented via a deep learning–based autoencoder employing successive interference cancellation, with a security layer constructed from universal hash functions, yielding a parallel-decodable two-layer coding architecture. By uniquely combining deep learning and universal hashing, the proposed approach significantly reduces training time and effectively suppresses information leakage even at short block lengths. The framework is further extended to multiple-access wiretap channels, demonstrating its practical efficacy and superiority in realistic communication scenarios.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Search and Optimization: Learning to Search
• Game Theory and Economic Paradigms: Adversarial Learning

Application Category

• Security and Privacy: Large-scale security measurements
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Consider the Gaussian wiretap channel, where a transmitter wishes to send a confidential message to a legitimate receiver in the presence of an eavesdropper. 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 codes that do not consider a helper. Our code design approach relies on a reliability layer, implemented with an autoencoder architecture based on the successive interference cancellation method, and a security layer implemented with universal hash functions. We also propose an alternative autoencoder architecture that significantly reduces training time by allowing the decoders to independently estimate messages without successively canceling interference by the receiver during training. Additionally, we show that our code design is also applicable to the multiple access wiretap channel with helpers, where two transmitters send confidential messages to the legitimate receiver.

Problem

• Gaussian wiretap channel
• secrecy rate
• eavesdropper
• helper-assisted coding
• information leakage

Innovation

• Helper-assisted coding
• Deep learning for physical layer security
• Autoencoder-based codes
• Universal hash functions
• Short blocklength secrecy