arXiv subjects

Hongwei Cui

Publications and source records attributed to Hongwei Cui.

4 recordsLinked to original sources

arXiv2026

LightGuard: Transparent WiFi Security via Physical-Layer LiFi Key Bootstrapping

WiFi is inherently vulnerable to eavesdropping because RF signals may penetrate many physical boundaries, such as walls and floors. LiFi, by contrast, is an optical method confined to line-of-sight and blocked by opaque surfaces. We present LightGuard, a dual-link architecture built on this insight: cryptographic key establishment can be offloaded from WiFi to a physically confined LiFi channel to mitigate the risk of key exposure over RF. LightGuard derives session keys over a LiFi link and installs them on the WiFi interface, ensuring cryptographic material never traverses the open RF medium. A prototype with off-the-shelf WiFi NICs and our LiFi transceiver frontend validates the design.

cs.CR↗

arXiv2025

LLMind 2.0: Distributed IoT Automation with Natural Language M2M Communication and Lightweight LLM Agents

Recent advances in large language models (LLMs) have generated great interest in their applications for IoT automation and device management. However, centralized approaches struggle to scale across heterogeneous, large-scale systems. We present LLMind 2.0, a distributed framework that embeds lightweight LLM-empowered device agents and adopts natural language for machine-to-machine (M2M) communication. In LLMind 2.0, a central coordinator translates human instructions into natural-language subtask descriptions, which instruct distributed device agents to generate device-specific code locally based on their proprietary APIs. Using natural language as a unified medium overcomes device heterogeneity and enables seamless device collaboration. LLMind 2.0 integrates: 1) a timeout-based deadlock avoidance protocol that coordinates distributed subtask executions, 2) a retrieval-augmented generation (RAG) mechanism for precise subtask-to-API mapping, and 3) fine-tuned lightweight LLMs for reliable, device-specific code generation. Experiments in multi-robot warehouse operations and Wi Fi network deployments show LLMind 2.0 improved scalability, reliability, and responsiveness compared to centralized baselines.

eess.SY↗

arXiv2025

Optical Wireless Ether: Enabling Controlled Dynamic Signal Propagation in OWC Systems

Optical wireless communication (OWC) leverages the terahertz-scale optical spectrum to enable ultra-fast data transfer, offering a compelling alternative to often-congested radio frequency systems. However, the highly directional nature of optical signals and their susceptibility to obstruction inherently limit coverage and reliability, particularly in dynamic indoor environments. To overcome these limitations, we propose optical wireless ether (OWE), a novel framework that transforms indoor spaces into a dynamically controllable optical propagation medium. OWE employs a distributed network of ether amplifiers (EAs), which act as optical amplifiers with programmable gain values to extend coverage through diffuse reflections while compensating for signal attenuation. A key challenge in OWE is preventing amplifier saturation from feedback loops. We rigorously derive stability constraints to guarantee system robustness. Beyond coverage extension, OWE dynamically adjusts EA gains in response to user locations and channel conditions, enhancing signal-to-noise ratio, balancing resource allocation, and suppressing interference. As the first framework to harness diffuse reflection for controllable optical propagation, we validate OWE's effectiveness through analytical modeling, simulations, and prototyping. Our work lays the foundation for robust, high-speed indoor OWC networks.

eess.SY↗

arXiv2023

LLMind: Orchestrating AI and IoT with LLM for Complex Task Execution

Task-oriented communications are an important element in future intelligent IoT systems. Existing IoT systems, however, are limited in their capacity to handle complex tasks, particularly in their interactions with humans to accomplish these tasks. In this paper, we present LLMind, an LLM-based task-oriented AI agent framework that enables effective collaboration among IoT devices, with humans communicating high-level verbal instructions, to perform complex tasks. Inspired by the functional specialization theory of the brain, our framework integrates an LLM with domain-specific AI modules, enhancing its capabilities. Complex tasks, which may involve collaborations of multiple domain-specific AI modules and IoT devices, are executed through a control script generated by the LLM using a Language-Code transformation approach, which first converts language descriptions to an intermediate finite-state machine (FSM) before final precise transformation to code. Furthermore, the framework incorporates a novel experience accumulation mechanism to enhance response speed and effectiveness, allowing the framework to evolve and become progressively sophisticated through continuing user and machine interactions.

cs.IT↗