A Study on Machine Learning-Based Models for Cyber Attack Classification and Severity Estimation

The increasing complexity and frequency of cyber threats have rendered traditional rule-based security approaches inadequate.Machine Learning (ML) has emerged as a powerful solution, offering automated detection, prediction, and mitigation of cyberattacks by learning from data patterns.This study explores the application of ML techniques, focusing on linear regression for predicting continuous threat severity and logistic regression for binary attack classification.Using a cybersecurity dataset, both models demonstrate high accuracy and effective performance in their respective tasks.The study discusses the strengths and limitations of these models, emphasizing the need for larger, more diverse datasets to enhance real-world applicability.Finally, it outlines future directions for integrating advanced ML algorithms into adaptive security frameworks to build more resilient cyber defense systems.