🤖 AI Summary
This work addresses the security challenges in LLM-enabled edge networks, where frequent wireless interactions and electromagnetic emissions render systems vulnerable to eavesdropping, interference, and prompt injection attacks, while existing defenses incur prohibitive overhead. To overcome this limitation, the paper introduces— for the first time—a lightweight security framework that synergistically integrates covert communication principles with computation. By jointly incorporating electromagnetic leakage suppression, low-overhead encryption, and secure scheduling strategies, the proposed approach simultaneously preserves the privacy of LLM tasks and significantly enhances execution efficiency. Experimental results demonstrate that under stringent security constraints, the method effectively reduces overall latency, achieving a co-optimized balance between security and performance and thereby transcending conventional high-overhead protection paradigms.
📝 Abstract
Large language model (LLM)-enabled edge networks (LLMENs) offer mobile users high-quality and low-latency AI-generated content services in the 6G era. However, unlike typical edge networks, LLMENs present unique security challenges due to the inherent complexity of LLMs, their high computational overhead, and continuous interactions with users. Specifically, both frequent user interactions (i.e., queries and responses) over wireless channels and potential electromagnetic information leakage from intensive LLM computations make LLMENs susceptible to various security threats, such as eavesdropping, jamming, prompt poisoning, and prompt injection attacks. Since existing countermeasures against these attacks often incur prohibitive overhead, developing holistic, efficient, and secure privacy protections for LLMENs is crucial. This article first reviews the vulnerabilities of LLMENs, outlines various attacks, and analyzes the drawbacks of existing countermeasures. To overcome these limitations, we propose a covert communications (CC) and computations approach to enhance both the overall security and efficiency of LLMENs. Furthermore, various supplementary solutions are developed to improve the covertness of this framework. Finally, our approach is further evaluated through a case study where the total latency is minimized under stringent communication and computational security requirements. Numerical results demonstrate the proposed approach's effectiveness in enhancing both privacy protection and the execution efficiency of LLM tasks.