Robust Intrusion Detection for Smart Agriculture Networks using CatBoost and Adversarial Training

View at publisher Summarise with VIRAT
Authors: Janani S. R. Sakthi, Priya Vedhanayagam
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Incorporating Internet of Things (IoT) devices into agriculture has enabled conventional farming practices, transforming them into smart farming systems that facilitate the real-time monitoring of soil, weather, crops, and livestock to enhance productivity. Even so, this increased connectivity introduces cybersecurity vulnerabilities, which pose threats to sensitive agricultural instances and operations. To strengthen the security of Internet of Things based smart farming networks, this study demonstrates an advanced threat detection framework relies on the CatBoost classifier chosen for its flawless capability in handling categorical data. The Effectiveness of CatBoost was further optimized using Optuna for automated hyperparameter tuning in conjunction with adversarial training techniques to enhance its adaptability against malicious attacks. Experimental results indicate that the CatBoost based system achieves 93.5% accuracy in identifying security threats, exceeding other examined algorithms, including XGBoost and Extra Trees classifiers. Along with, adversarial training claims a system accuracy above 92% under simulated attack conditions, demonstrating robust threat detection capacities. This study represents the potential of the optimized CatBoost model to significantly enhance the cybersecurity approach of smart farming environment, thereby ensuring safer and more reliable agricultural operations in an increasingly connected to smart farming environment.

Fields of Study & Subjects

Network Security and Intrusion Detection Smart Agriculture and AI Internet of Things and AI

Publication details

Journal / source
CRC Press eBooks
Pages
533–540
Publication date
31 March 2026
Language
EN
Document type
Book chapter