Wormhole Attack Detection in the Internet of Things Using a Hybrid Deep Learning Model

Internet growth has led to widespread adoption and transmission of the IoT in numerous areas. From personal networks to industrial applications., healthcare to transportation., IoT is everywhere. Due to their widespread usage., attackers deploy sophisticated methods and software to infiltrate IoT networks. IoT devices' low processing power and resources can threaten security and privacy. This vulnerability has inspired attackers to undertake a variety of attacks against IoT networks. Wormhole attacks (WHA) are routing attacks which can interrupt IoT network packet routing and flow. To address the security issues related to IoT devices., a novel hybrid deep Learning (DL) method is proposed to classify potential security risks in IoT circumstances. The proposed module combines the Bidirectional Long Short-Term Memory with attention mechanism (ABS-BiLSTM) and AlexNet CNN to achieve higher detection accuracy. The security service provided by the proposed monitoring solution ensures compatibility among various IoT network communication protocols. The results clearly show that the effectiveness and excellence of the schemes in terms of network performance., accuracy., and detection speed enhancement.