Location
https://www.kennesaw.edu/ccse/events/computing-showcase/fa24-cday-program.php
Document Type
Event
Start Date
19-11-2024 4:00 PM
Description
The growing complexity and volume of network traffic pose significant challenges to traditional intrusion detection systems (IDS), often leading to inefficiencies in detecting unauthorized access and malicious activities. To identify different types of network attacks, many intrusion detection systems (IDSs) have been proposed using artificial intelligence or machine learning, but the results are still not satisfactory for most of these systems. Recently in some research, deep learning models have shown promising performance in big data analysis. However, a combined data mining and deep learning approach in big data for the detection of intrusions has not been scrutinized. This research aims to develop a hybrid approach combining data mining techniques and deep learning models to improve the detection of intrusions in large-scale networks. In this paper, we propose a Genetic Algorithm (GA) and Minimum Redundancy Maximum Relevance (mRMR) to select optimal features by reducing the dimensionality of the dataset. Initially (mRMR) selects features based on high relevance to the target variable and also has the minimum overlapping information of those selected features. Then GA algorithm finds the best subset of features where it evaluates the various combinations of attributes and chooses the best ones to enhance the performance of the model. After that, the deep learning model Convolutional Neural Network (CNN) was introduced, which uses 1D convolutional layers to detect small, localized complex patterns by adopting structured data. By leveraging data mining for feature extraction and deep learning for anomaly detection, the proposed system seeks to enhance the accuracy and efficiency of IDS in handling big data. The expected results include improved detection rates, reduced false positives, and robust performance in processing large network intrusion datasets.
Included in
GMC-168 Hybrid Approach of Data Mining and Deep Learning for Network Intrusion Classification in Big Data
https://www.kennesaw.edu/ccse/events/computing-showcase/fa24-cday-program.php
The growing complexity and volume of network traffic pose significant challenges to traditional intrusion detection systems (IDS), often leading to inefficiencies in detecting unauthorized access and malicious activities. To identify different types of network attacks, many intrusion detection systems (IDSs) have been proposed using artificial intelligence or machine learning, but the results are still not satisfactory for most of these systems. Recently in some research, deep learning models have shown promising performance in big data analysis. However, a combined data mining and deep learning approach in big data for the detection of intrusions has not been scrutinized. This research aims to develop a hybrid approach combining data mining techniques and deep learning models to improve the detection of intrusions in large-scale networks. In this paper, we propose a Genetic Algorithm (GA) and Minimum Redundancy Maximum Relevance (mRMR) to select optimal features by reducing the dimensionality of the dataset. Initially (mRMR) selects features based on high relevance to the target variable and also has the minimum overlapping information of those selected features. Then GA algorithm finds the best subset of features where it evaluates the various combinations of attributes and chooses the best ones to enhance the performance of the model. After that, the deep learning model Convolutional Neural Network (CNN) was introduced, which uses 1D convolutional layers to detect small, localized complex patterns by adopting structured data. By leveraging data mining for feature extraction and deep learning for anomaly detection, the proposed system seeks to enhance the accuracy and efficiency of IDS in handling big data. The expected results include improved detection rates, reduced false positives, and robust performance in processing large network intrusion datasets.