Publication Date
Spring 2025
Degree Type
Master's Project
Degree Name
Master of Science in Computer Science (MSCS)
Department
Computer Science
First Advisor
Fabio Di Troia
Second Advisor
Navrati Saxena
Third Advisor
Sai Eshwar Reddy Vakka
Keywords
Botnet, Synthetic network traffic, Intrusion detection, Data augmentation, Cybersecurity.
Abstract
Though botnet attacks are on the rise, they also have become sophisticated and difficult to detect. Such a rising threat demands more and more sophisticated cybersecurity that leverages machine learning technology. Nevertheless, one of the biggest bottlenecks remains the unavailability of large and well-balanced datasets, particularly for malicious traffic, which hampers the efficacy of detection models. In an attempt to address this issue, our research utilizes Generative Adversarial Networks (GANs) to produce synthetic samples of botnet traffic from the CTU-13 dataset. While the majority of generative models have been targeting image data, we use GANs for a new application: generating flow-based network traffic records that mimic actual botnet activity. These generated records are intended to mimic actual attacks as closely as possible, thereby addressing the scarcity of data and enhancing the classifier’s training. Different machine learning algorithms like Random Forests, Decision Trees, and Deep Neural Networks are trained on both real and synthetic data, demonstrating considerable improvements in identifying infrequent botnet patterns. Motivated by some of the recent results on the application of GANs to intrusion detection and malware, our paper highlights the capabilities of synthetic data to improve the accuracy and generalization of security models. First, results suggest that not only do these artificial samples look realistic, but they also fool regular detection tools, proving that this technique may help in developing more robust and persistent botnet detection systems.
Recommended Citation
Maturu, Aneesh, "Gen Ai for Malicious Network Data" (2025). Master's Projects. 1555.
DOI: https://doi.org/10.31979/etd.s4qz-2t8c
https://scholarworks.sjsu.edu/etd_projects/1555
