Adaptive Dual-Path Framework for Covert Semantic Communication

2026-05-05

AI Summary

This work addresses the challenge of achieving secure and covert information transmission while performing semantic communication tasks. To this end, the authors propose an adaptive dual-path framework: an explicit path handles public semantic tasks, while a steganographic path embeds secret messages into task-relevant semantic features. Semantic consistency between the two paths is preserved through contrastive representation alignment, and Gumbel-Softmax is leveraged to enable task-driven, adaptive module selection. This approach represents the first method to realize high-security covert communication at the semantic level. Evaluated on the Cityscapes dataset, it reduces the adversary’s detection accuracy to 56.12%—close to random guessing—while simultaneously outperforming existing baselines in the primary semantic task.

Abstract

This paper proposes a novel adaptive dual-path framework for covert semantic communication (SemCom), which integrates covert information transmission with task-oriented semantic coding. Unlike conventional covert communication methods that embed hidden messages through power-domain signal superposition, our framework embeds covert data within task-specific features via semantic-level intrinsic encoding. This new architecture introduces dual encoding paths with adaptive block selection: an Explicit path for public task execution and a Stego path that jointly encodes both public and covert information through contrastive representation alignment. A Gumbel-Softmax enabled adaptive path selection mechanism dynamically activates network blocks based on task require- ments. We formulate a multi-objective optimization framework that simultaneously ensures accurate semantic understanding and reliable covert transmission. We rigorously evaluate our framework's security against a powerful, independently trained attacker. Experimental results on the Cityscapes dataset demon- strate a state-of-the-art level of covertness: our method suppresses the attacker's detection accuracy to a near-random guessing level of 56.12%. This robust security is achieved while simultaneously maintaining superior performance on the primary semantic tasks compared to the baselines.

Problem

• covert communication
• semantic communication
• steganography
• task-oriented
• information hiding

Innovation

• covert semantic communication
• adaptive dual-path framework
• semantic-level intrinsic encoding
• contrastive representation alignment
• Gumbel-Softmax path selection