ENHANCING CYBERSECURITY THREAT DETECTION: A COMPARATIVE STUDY OF DEEP LEARNING AND MACHINE LEARNING
Keywords:
Cyber Threat Intelligence, Machine Learning Models, Deep Learning Techniques, Logistic Regression, K Nearest Neighbors (KNN), Gaussian Naïve Bayes (GNB), Support Vector Machines (SVM), Convolutional Neural Network (CNN)Abstract
The goal of this Paper is to improve cybersecurity threat detection by thoroughly examining deep learning and machine learning
models. The study attempts to solve the difficulty of precisely categorizing and forecasting hostile actions in network traffic
by focusing on a dataset that encompasses a variety of cyber threats. Preprocessing the data, using Principal Component
Analysis (PCA) to apply dimensionality reduction, and putting a variety of machine learning algorithms into practice—
including Logistic Regression, K-Nearest Neighbours, Gaussian Naive Bayes, Support Vector Machines, Decision Trees, and
Random Forest—are all part of the methodology. Important conclusions highlight how ensemble models— Random Forest in
particular—work well to achieve notable precision and accuracy. Principal Component Analysis's effect on model performance
is also examined, providing information about the significance of features and the interpretability of the model. In addition to
highlighting the promise of ensemble methods for reliable threat detection, the research provides insightful information about
the efficacy of different machine learning algorithms in cybersecurity. The study’s insights have practical consequences for
cybersecurity practitioners and lay the groundwork for future cybersecurity analytics research projects.
