Shadow Wireless Intelligence: Large Language Model-Driven Reasoning in Covert Communications

2025-05-07

AI Summary

To address the poor adaptability and limited real-time responsiveness of conventional covert communication techniques—such as artificial noise (AN) injection and channel manipulation—in dynamic, adversarial 6G environments, this paper pioneers the integration of large language models (LLMs) into the decision-making closed loop of wireless covert systems. We propose a retrieval-augmented, LLM-driven paradigm: (i) constructing a structured covert communication knowledge base to enable semantic-level strategy generation; (ii) synergistically combining reinforcement learning (RL)-enhanced reasoning with domain-specific knowledge retrieval to mitigate hallucination; and (iii) designing a full-duplex AN power optimization framework grounded in semantic control. Leveraging DeepSeek-R1 (MoE architecture fine-tuned via RL) augmented with RAG, our approach achieves 85% symbol derivation accuracy and 94% correct simulation code generation under full-duplex operation—demonstrating substantial improvements in robustness, interpretability, and real-time adaptive capability.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Large language models for search
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Covert Communications (CC) can secure sensitive transmissions in industrial, military, and mission-critical applications within 6G wireless networks. However, traditional optimization methods based on Artificial Noise (AN), power control, and channel manipulation might not adapt to dynamic and adversarial environments due to the high dimensionality, nonlinearity, and stringent real-time covertness requirements. To bridge this gap, we introduce Shadow Wireless Intelligence (SWI), which integrates the reasoning capabilities of Large Language Models (LLMs) with retrieval-augmented generation to enable intelligent decision-making in covert wireless systems. Specifically, we utilize DeepSeek-R1, a mixture-of-experts-based LLM with RL-enhanced reasoning, combined with real-time retrieval of domain-specific knowledge to improve context accuracy and mitigate hallucinations. Our approach develops a structured CC knowledge base, supports context-aware retrieval, and performs semantic optimization, allowing LLMs to generate and adapt CC strategies in real time. In a case study on optimizing AN power in a full-duplex CC scenario, DeepSeek-R1 achieves 85% symbolic derivation accuracy and 94% correctness in the generation of simulation code, outperforming baseline models. These results validate SWI as a robust, interpretable, and adaptive foundation for LLM-driven intelligent covert wireless systems in 6G networks.

Problem

• Adapting covert communications to dynamic adversarial 6G environments
• Overcoming limitations of traditional AN-based optimization methods
• Enabling real-time intelligent decision-making in covert wireless systems

Innovation

• LLM-driven reasoning for covert wireless intelligence
• Retrieval-augmented generation for domain-specific accuracy
• RL-enhanced mixture-of-experts model for real-time adaptation