Deep Learning-Based Defense Mechanisms Against Black Hole Attacks in Wireless Mesh Networks

Abstract

Wireless Mesh Networks (WMNs) are susceptible to various security threats, including black hole attacks, where malicious nodes attract and drop packets, disrupting network communication. Traditional security mechanisms are often inadequate in detecting and mitigating these attacks due to their dynamic and evolving nature. In this paper, we propose a novel deep learning-based defense mechanism against black hole attacks in WMNs. It utilizes Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM) networks to analyze network traffic patterns and detect abnormal behavior indicative of black hole attacks. The proposed approach offers several advantages, including the ability to adapt to new attack patterns and achieve high detection accuracy. We evaluate our method using a real-world dataset and demonstrate its effectiveness in mitigating black hole attacks. Our results show that the proposed deep learning-based defense mechanism can accurately detect and mitigate black hole attacks, thus enhancing the security and reliability of WMNs.