BLM-Chain: AI-Driven Blockchain for UAV Threat Resistance in IoBT

The rapid expansion of the Internet of Battlefield Things (IoBT) has introduced significant vulnerabilities, particularly concerning unmanned aerial vehicles (UAVs) that are increasingly targeted by sophisticated cyber threats. To address these challenges, this paper proposes the BLM-Chain framework. This novel approach integrates blockchain technology with large language models (LLMs) to enhance UAV threat resistance within IoBT networks. The framework leverages blockchain's immutable and decentralized nature to ensure secure, transpar-ent, and tamper-proof data handling across distributed IoBT nodes. Concurrently, LLMs are employed for advanced, context-aware intrusion detection, capable of identifying complex threat patterns that conventional methods may overlook. The impact of convolutional neural networks (CNNs) within the framework is crucial for deep feature extraction, allowing the system to identify and prioritize the most relevant data features for accurate threat detection. Blockchain-based smart contracts further reinforce the system's robustness and automate real-time responses to detected threats, enhancing operational efficiency in dynamic battlefield environments. Experimental results, evaluated on the 5G-NIDD dataset, demonstrate the BLM-Chain model's superior performance, achieving higher accuracy, precision, recall, and F1-scores than existing threat resistance models. This study presents a significant advancement in securing IoBT networks, offering a scalable, decentralized, and efficient solution to UAV cybersecurity threats.