Unveiling Covert Semantics: Joint Source-Channel Coding Under a Covertness Constraint

TL;DR

This paper establishes the fundamental limits of covert semantic communication using joint source-channel coding, demonstrating theoretical bounds and practical neural network-based approaches that adhere to covertness constraints.

Contribution

It provides the first information-theoretic analysis of covert semantic communication, showing source-channel separation and the square-root scaling law for reliable transmission.

Findings

Achievability and converse bounds for covert semantic communication.

Neural network training achieves covert classification tasks.

Transmission scales with the square root of channel uses.

Abstract

The fundamental limit of Semantic Communications (joint source-channel coding) is established when the transmission needs to be kept covert from an external warden. We derive information-theoretic achievability and matching converse results and we show that source and channel coding separation holds for this setup. Furthermore, we show through an experimental setup that one can train a deep neural network to achieve covert semantic communication for the classification task. Our numerical experiments confirm our theoretical findings, which indicate that for reliable joint source-channel coding the number of transmitted source symbols can only scale as the square-root of the number of channel uses.