STLGBM-DDS: An Efficient Data Balanced DoS Detection System for Wireless Sensor Networks on Big Data Environment

Abstract

Wireless Sensor Networks(WSNs) are vulnerable to a variety of unique security risks and threats in their data collection and transmission processes. One of the most common attacks on WSNs that can target all layers of the protocol stack is the DoS attack. In this study, a unique DoS Intrusion Detection System (DDS) is proposed to detect DoS attacks specific to WSNs. The proposed system is an ensemble intrusion detection system called STLGBM-DDS, which is developed on Apache Spark big data platform in Google Colab environment, combining LightGBM machine learning algorithm, data balancing and feature selection processes. In order to reduce the effects of data imbalance on system performance, data imbalance processing consisting of Synthetic Minority Oversampling Technique (SMOTE) and Tomek-Links sampling methods called STL was used. In addition, Information Gain Ratio was used as a feature selection technique in the data preprocessing stage. The effects of both data balancing and feature selection stages on the detection performance of the system were investigated. The results obtained were evaluated using the Accuracy, F-Measure, Precision, Recall, ROC Curve and Precision-Recall Curve parameters. As a result, the proposed method achieved an overall accuracy of 99.95%. Also, it achieved 99.99%, 99.96%, 99.98%, 99.92%, 99.87% accuracy performance according to Normal, Grayhole, Blackhole, TDMA and Flooding classes, respectively. According to the results obtained, the proposed method has achieved very successful results in DoS attack detection in WSNs compared to current methods.

IoT-Based Intrusion Detection System Using New Hybrid Deep Learning Algorithm

“…Therefore, the IDSs to be used in WSNs must be designed with these limitations in mind. In the literature, there are IDS systems developed for WSNs using classification, clustering, machine learning, and statistical learning algorithms [1]. This section provides a summary of the IDS studies developed for detecting DDoS in WSNs.…”

“…A wireless data network is part of the Internet of Things (IoT), and the collected data are processed, analyzed, and presented to the user with the help of a base station. A WSN typically includes at least one gateway node that serves as a link between the network and the external world [1].…”

A Hybrid Rider Optimization with Deep Learning Driven Intrusion Detection Farmwork in Wireless Sensor Network

“…Dener et al (28) to identify DoS assaults targeted at WSNs, a special DoS IDS (DDS) has been suggested. The LightGBM ML procedure, data balancing, and FS (Feature Selection) are used by the ensemble IDS STLGBM-DDS.…”

Improving Data Transmission Rate with Self Healing Activation Model for Intrusion Detection with Enhanced Quality of Service

“…However, deploying big data-enabled intrusion detection algorithms on resource-constrained edge nodes in IoT is crucial for assuring the high accuracy of IDS [34]. Fuzzy rough sets, Generative Adversarial Networks (GANs), and Convolutional Neural Networks (CNNs) are proposed by Wu et al [8] as a massive data mining solution to the aforementioned problems in intrusion detection. First, the author presented an approach based on fuzzy rough sets to carry out feature selection for big data using the Internet of Things.…”

“…Traditional methods of intrusion protection involve looking for the virus's signature in certain locations. While it is undeniable that the traditional method should be utilized to protect against known dangers [7], it does not offer security against zero-day vulnerabilities, which are new assaults that have not been discovered and do not yet have a deployed security patch [8]. The attack cannot be positively identified since antivirus programs do not yet recognize their signature.…”