An Intrusion Detection System for Edge-Envisioned Smart Agriculture in Extreme Environment

The deployment of Internet Things (IoT) systems in Smart Agriculture (SA) operates extreme environments including wind, snowfall, flooding, landscape, and so on for collecting processing real-time data. increased connectivity broad adoption IoT devices with low-power communications farmland support farmers making data-driven decisions using various Artificial Intelligence (AI) techniques. Furthermore, such an environment, edge computing is also utilized to provide computationally intensive, latency-sensitive, bandwidth-demanding services at the network. However, protecting edge-to-Things environment SA challenging, due volume data, attackers exploit network gateways perform Distributed Denial Service (DDoS) attacks. Motivated by aforementioned challenges, we develop a novel deep learning-based Intrusion Detection System (IDS) edge-envisioned environments. Specifically, hybrid approach developed combining bidirectional gated recurrent unit, long-short term memory softmax classifier detect attacks To allow faster learning, proposed IDS employs Truncated Backpropagation through Time (TBPTT) handle lengthy sequences suggest attack scenario architecture SA. Extensive experiments three publicly available datasets namely, CIC-IDS2018, ToN-IoT, Edge-IIoTset prove effectiveness over some traditional contemporary state-of-the-art