Implementation of a Hierarchical Hybrid Intrusion Detection Mechanism in Wireless Sensors Network

Abstract

Abstract-During the last years, Wireless Sensor Networks (WSNs) have attracted considerable attention within the scientific community. The applications based on Wireless Sensor Networks, whose areas include, agriculture, military, hospitality management, etc. are growing swiftly. Yet, they are vulnerable to various security threats, like Denial Of Service (DOS) attacks. Such issues can affect and absolutely degrade the performances and cause a dysfunction of the network and its components. However, key management, authentication and secure routing protocols aren't able to offer the required security for WSNs. In fact, all they can offer is a first line of defense especially against outside attacks. Therefore, the implementation of a second line of defense, which is the Intrusion Detection System (IDS), is deemed necessary as part of an integrated approach, to secure the network against malicious and abnormal behaviors of intruders, hence the goal of this paper. This allows improving security and protecting all resources related to a WSN. Recently, different detection methods have been proposed to develop an effective intrusion detection system for WSNs. In this regard, we proposed an integral mechanism which is an hybrid Intrusion Detection approach based on anomaly, detection using support vector machine (SVM), specifications based technique, signature and clustering algorithm to decrease the consumption of resources, by reducing the amount of information forwarded. So, our aim is to protect WSN, without disturbing networks performances through a good management of their resources, especially the energy.

Blockchain-Based Secure Localization against Malicious Nodes in IoT-Based Wireless Sensor Networks Using Federated Learning

“…Support Vector Machine. The term "support vector machine" (SVM) refers to a family of statistical methods for categorizing network activity under the guidance of an experienced teacher [52]. The fundamental purpose of a support vector machine (SVM) classifier is to build a hyperplane in the feature spaces using a set of vectors called support vectors.…”