ENHANCED SYSTEM FOR DETECTING INTRUSIONS USING SUPERVISED LEARNING

Computer Engineering

The increasing prevalence of cyber threats in the field of cyber security calls for the creation of strong Intrusion Detection Systems (IDS) in order to protect confidential digital information. With a focus on the NSL KDD Cyber Security dataset, this research offers a novel approach to IDS by using machine learning (ML) and deep learning (DL) approaches. The dataset is well known for providing a thorough representation of network traffic data and is a useful tool for testing and training intrusion detection algorithms. The effectiveness of an extensive number of deep learning (DL), and machine learning (ML), such as Ridge Classifier, K Nearest Neighbour, Nearest Centroid, Decision Tree, Naive Bayes, Support Vector Machine (SVM), Logistic Regression, Multi-layer Perceptron (MLP), Stochastic Gradient Descent (SGD), Regressor Neural Networks, Random Forest, Adaboost, and various neural network architectures, in identifying intrusions within network traffic is assessed in this study. Finding the most effective intrusion detection methods for real-world applications is the aim of this study., advancing cybersecurity procedures and safeguarding vital digital infrastructures via thorough testing and performance assessment.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.