# Adaptive Dual-Path Framework for Covert Semantic Communication

arXiv: https://arxiv.org/abs/2605.03423 · HTML: https://mlsanity.com/paper/2605.03423/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 48 references that are in the map.
- First posted on arXiv 5 May 2026.

## Builds on (most cited first, 16 of 16)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Beyond Transmitting Bits: Context, Semantics, and Task-Oriented Communications](https://mlsanity.com/paper/2207.09353/) (2022)
- [AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning](https://mlsanity.com/paper/1911.12423/) (2019)
- [Mitigating Information Leakage in Image Representations: A Maximum Entropy Approach](https://mlsanity.com/paper/1904.05514/) (2019)
- [A Unified Multi-Task Semantic Communication System for Multimodal Data](https://mlsanity.com/paper/2209.07689/) (2022)
- [Deep Joint Source-Channel and Encryption Coding: Secure Semantic Communications](https://mlsanity.com/paper/2208.09245/) (2022)
- [Rethinking Wireless Communication Security in Semantic Internet of Things](https://mlsanity.com/paper/2210.04474/) (2022)
- [Secure Semantic Communications: Fundamentals and Challenges](https://mlsanity.com/paper/2301.01421/) (2023)
- [Privacy-Aware Communication Over a Wiretap Channel with Generative Networks](https://mlsanity.com/paper/2110.04094/) (2021)
- [Scalable Multi-task Semantic Communication System with Feature Importance Ranking](https://mlsanity.com/paper/2304.05882/) (2023)
- [Landscape More Secure Than Portrait? Zooming Into the Directionality of Digital Images With Security Implications](https://mlsanity.com/paper/2406.15206/) (2024)
- [Learning-based Power Control for Secure Covert Semantic Communication](https://mlsanity.com/paper/2407.07475/) (2024)
- [Delay-Constrained Covert Communications with A Full-Duplex Receiver](https://mlsanity.com/paper/1810.05949/) (2018)

## Built on by (most cited first, 1 of 1)

- [Decentralized Federated Learning for Heterogeneous Multi-Task Semantic Communication](https://mlsanity.com/paper/2608.15256/) (2026)

## Abstract (arXiv)

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.