Secure AI-Driven Corn Disease Detection in 5G/6G-Enabled Smart Agriculture : Integrating Deep Learning and IoT Sensor Networks.

Abstract

The integration of Artificial Intelligence (AI) into smart agriculture has significantly enhanced crop monitoring and disease management, particularly for staple crops such as corn. However, the increasing reliance on interconnected Internet of Things (IoT) sensor networks and next-generation communication technologies, including 5G and emerging 6G systems, introduces critical security and privacy challenges. This paper presents a comprehensive review of secure AI-driven approaches for corn disease detection, focusing on the convergence of deep learning techniques, IoT-based sensing infrastructures, and 5G/6G-enabled smart agriculture frameworks. The study systematically analyses state-of-the-art deep learning models, including convolutional neural networks (CNNs), vision transformers, and hybrid architectures, for accurate and early-stage disease identification using image and multimodal sensor data. Furthermore, it explores the role of IoT sensor networks in real-time environmental monitoring and data acquisition, enabling precision agriculture practices. A key contribution of this review is the examination of security vulnerabilities across the data pipeline, including data poisoning, adversarial attacks, model inversion, and communication-level threats within 5G/6G networks. In addition, the paper discusses emerging security mechanisms such as blockchain-based data integrity, federated learning for privacy preservation, and intrusion detection systems (IDS) tailored for agricultural IoT environments. The challenges of scalability, latency, energy efficiency, and secure data transmission in ultra-reliable low-latency communication (URLLC) scenarios are also highlighted. Finally, open research issues and future directions are identified, emphasizing the need for robust, secure, and intelligent frameworks to ensure resilient and trustworthy smart agriculture systems.