Integrity Assessment and Intrusion Detection Using ACGAN-Powered Machine Learning

This study investigates the use of Auxiliary Classifier Generative Adversarial Networks (ACGANs) in addressing imbalanced data within the realm of cybersecurity. ACGANs generate synthetic data mimicking network attacks, contributing to dataset balancing for improved model training. The research focuses on enhancing cybersecurity decision making by refining the accuracy of distinguishing between legitimate and malicious traffic. By leveraging ACGAN-powered machine learning, this project work demonstrates the potential for stronger, more accurate threat detection and integrity assessment, ultimately fostering more advanced and resilient intrusion detection systems.