Analyzing and Mitigation of Cybersecurity Threats and Risks in Precision Agriculture Through IoT and AI Techniques

A Perspective on Security of Smart Farming: Attacks and Countermeasures

The integration of technologies like the Internet of Things (IoT) and Artificial Intelligence (AI) is fueling a shift toward smart farming, unlocking a fundamental change in how agriculture is practiced through new precision agriculture techniques. While these innovations enhance efficiency and streamline routine agricultural operations, they also introduce a range of new threats and vulnerabilities within smart farming ecosystems. This research differentiates itself within the field of smart farming security. It achieves this through an integrated examination of systemic vulnerabilities across the entire agricultural technology stack. Organized into four core sections, i.e., sensing, network, cloud, and application layers, it systematically identifies the specific security risks associated with each layer, including data leakage, signal injection, cyberattacks, and manipulation of artificial intelligence systems. The paper further discusses appropriate countermeasures designed to mitigate these risks and underscores the importance of adopting integrated defense strategies. By analyzing current cybersecurity trends and the application of artificial intelligence in protective mechanisms, the study provides valuable insights into future research pathways aimed at establishing secure and sustainable agricultural technologies.

From perception to reaction: an RLCC-engine-driven cybersecurity framework for smart agricultural ecosystems

Cybersecurity threats in IoT-enabled smart agriculture systems: A SOC-centric detection and mitigation framework

The emergence of cyber-physical systems in agricultural production has created unprecedented opportunities for precision farming while simultaneously introducing substantial security vulnerabilities. This research addresses the critical challenge of distinguishing sensor anomalies from malicious cyber-attacks in resource-constrained agricultural Internet of Things (IoT) environments. We propose a comprehensive Security Operations Center (SOC)-centric framework integrating signature-based detection, machine learning-based anomaly analysis, and novel fault-aware modeling within a multi-layered architecture specifically optimized for agricultural deployment scenarios. The framework's core innovation is a hybrid mathematical detection model that jointly analyzes anomaly scores and sensor fault probabilities, enabling differentiation between environmental sensor anomalies and cyber-attack signatures. Explainable Artificial Intelligence (XAI) modules utilizing SHAP (SHapley Additive exPlanations) and LIME (Local Interpretable Model-agnostic Explanations) enhance transparency in automated security decisions, addressing operational trust requirements in real-world farm deployments Experimental validation through containerized testbed simulations demonstrates exceptional performance: detection accuracy of 97.8%, precision of 96.4%, recall of 98.2%, F1-score of 0.972, and ROC-AUC of 0.989. The Fault-Attack Detectability Score (FADS) metric achieves mean performance of 0.910, indicating superior fault-attack differentiation capability. Comparative analysis reveals substantial improvements: 18.5% accuracy advantage over traditional intrusion detection systems, 12.3% improvement over machine learning autoencoder baselines, and 8.1% F1-score gain over random forest ensemble approaches. Resource efficiency analysis demonstrates practical viability for constrained agricultural deployments: 32% memory reduction, 87% network bandwidth reduction via edge processing, and 86% power consumption reduction. The framework provides a systematic, scalable, and explainable security solution that addresses the critical research gap between sensor health monitoring and cybersecurity management in Agriculture 4.0 systems.

A Unified Mathematical and IoT-Based Predictive Framework for Smart Fire Detection, Cybersecurity, and Precision Irrigation Systems

The rapid expansion of the Internet of Things (IoT) has enabled the development of intelligent systems capable of addressing complex challenges across public safety, agriculture, and digital security. However, most existing solutions are designed for individual applications and lack a unified framework that integrates multiple real-world domains with mathematical decision-making. This study proposes a unified mathematical and IoT-based predictive framework that combines smart fire detection, cybersecurity, privacy protection, precision irrigation, and cybercrime pattern analysis within a single architecture. The proposed framework employs interconnected IoT devices to collect and transmit real-time data from distributed environments, while mathematical modeling and predictive analysis support timely decision-making and efficient resource utilization. In the fire detection module, environmental sensors monitor parameters such as temperature, smoke, and gas concentration to enable early hazard identification. The precision irrigation module utilizes soil and weather information to optimize water distribution and improve agricultural productivity. To strengthen cyberspace security, the framework incorporates data protection mechanisms and analyzes cybercrime patterns to identify potential threats and support preventive actions. The integration of these components demonstrates how mathematical analysis and IoT technologies can enhance system reliability, operational efficiency, and decision accuracy across diverse application domains. The proposed framework provides a scalable and adaptable foundation for the development of secure and intelligent smart systems suitable for future smart cities, agriculture, and critical infrastructure.

Cybersecurity in aquaculture: Risks, governance, and future directions across production systems

Aquaculture is becoming increasingly dependent on connected sensors, remote monitoring, edge and cloud analytics, automation, and digital traceability; however, the cybersecurity evidence base remains fragmented and low‐trophic systems are markedly underrepresented. This systematic review synthesizes the literature on cyber risks, governance, and mitigation in aquaculture. The evidence shows that digitized aquaculture is primarily exposed through environmental sensor networks, wireless communications, cloud platforms, blockchain traceability systems, and emerging digital twins. The most recurrent threat families were data‐integrity attacks, network‐based attacks, authentication and access‐control failures, ransomware, and supply‐chain compromise. Mitigation strategies centered on lightweight encryption and mutual authentication for resource‐constrained devices, intrusion detection and monitoring, network segmentation, permissioned blockchain architectures, and privacy‐preserving edge or federated learning. However, only one study directly addressed mussel farming and no study focused specifically on seaweed farming. This gap is consequential because low‐trophic aquaculture is increasingly promoted for nutrient removal, climate adaptation, and food‐system resilience. We argue that aquaculture cybersecurity should be treated as a cyber‐physical and socio‐ecological problem: cyber incidents can distort environmental data, disrupt certification and traceability, and undermine both farm operations and ecosystem‐service claims. NIST risk‐management practices and ENISA/NIS 2‐aligned governance offer useful starting points, but they require aquaculture‐specific adaptation to remote marine operations and to the capacities of smaller producers. Future work should prioritize sector‐specific threat models, field validation, incident reporting, and secure‐by‐design architectures for low‐trophic farms.

Leveraging Internet of Things and Artificial Intelligence in Smart Agriculture to Enhance Food Security and Sustainable Farming: A Systematic Review

The review shows that AI-IoT technologies are primarily applied in crop disease detection, precision agriculture, environmental monitoring, yield prediction, and livestock health monitoring, and the five-layered framework introduced here provides the first inductively derived organising structure that explicitly connects AI-IoT infrastructure to SDG-aligned food security outcomes.