Towards a New Approach-Driven Intrusion Detection in IoT Network

Abstract

Noura Ben Henda, Imen Hagui and Abdelhamid Helali

The integration of Internet of Things (IoT) with artificial intelligence and smart devices (SD) in agriculture has revolutionized traditional farms and significantly improve the productivity and food production. Although the advantage offered by this combination, it still faces security challenges. To fix this problem and ensuring the resilience and reliability of smart agriculture (SA) systems, we propose an advanced network intrusion detection system (NIDS) to detect and address new threats in IoT networks. In this work, we design and evaluate a deep learning-based network intrusion detection system (DL-NIDS) that can successfully identify and detect intrusions in smart agriculture network. The experiment accomplished on three well known datasets namely, NSL-KDD, CIC-IDS-2017, and EdgeIIoTset, demonstrated the effectiveness of our system against the state-of-the-art approaches.

PDF