فهرست نشریات علمی دسترسی آزاد ایران

As a type of wireless network, mobile ad-hoc networks (MANETs) consist of mobile nodes that are able to move freely and independently in any direction and operate in a self-configurable and self-organizing manner, especially in situations such as natural disasters, military operations, or large social events that require rapid setup without the need for fixed infrastructure. are absolutely vital. However, these networks face numerous challenges and are naturally vulnerable due to the limited resources of nodes, such as energy, processing, and memory, as well as the lack of pre-designed infrastructure. This vulnerability can lead to a variety of attacks and security threats, one of which is One of the most common is black hole attacks. In these types of attacks, attackers attract network traffic by luring other nodes and then ignore or eliminate it entirely, which can seriously affect network performance. In this paper, a new approach to detect black hole attacks through anomaly detection techniques using response generation time and machine learning models is proposed. It continuously monitors the activities of nodes and examines and analyzes real-time network traffic, and uses machine learning algorithms to identify behavioral characteristics, irregularities, and abnormal activities and differentiate them from other nodes. Analysis of the results of the nightshades shows increased accuracy in detecting black hole attacks and ensuring the security of mobile Ad-hoc networks. This approach not only helps to detect attacks faster, but also increases the overall efficiency of the system.