Intrusion Detection System using Machine Learning Algorithms

As cyber threats evolve, the need for advanced network security systems has become critical.This project aims to develop a naive Intrusion Detection System (IDS) using penetration testing techniques and machine learning algorithms to enhance threat recognition and mitigation.The IDS employs algorithms like Logistic Regression, Support Vector Machines (SVM), and K-Nearest Neighbors (KNN) to detect and classify network intrusions.This paper focuses on a KNN-based approach, utilizing the UNSW-NB15 dataset for both simulated port attack traffic and normal traffic.The dataset undergoes pre-processing and normalization to ensure its readiness for model training.The data is then split into training and testing sets to evaluate the models' performance.Multiple models, including Logistic Regression, SVM, and KNN, are built and compared based on their accuracy, precision, and recall.This benchmark analysis helps assess the effectiveness of each model in identifying and classifying network attacks, ensuring that the IDS can accurately detect threats while minimizing false positives.The integration of machine learning in IDS development aims to enhance the overall robustness and responsiveness of network security systems in real-world environments.