Detecting Botnet Activity: Learning Discriminative Boosted Bayesian Networks for Accurate AnalysisVaishnavi Cherukuvada
Year: 2025
Type: article
Abstract: Distributed network attacks, including botnets, pose significant chal- lenges in detecting and mitigating their activities. We present the applicationof learning Discriminative Boosted Bayesian Networks to detect botnet activ-ity using the CTU-13-Dataset. Our results are compared with traditional machine learning approaches, with and without expert knowledge. This marks the first application of statistical relational learning in this domain, addressing the need for effective detection in evolving threat landscapes. Our approach focuses on learning a generalized model from sparse botnet data, addressing the challenges of limited data availability. By carefully engineering features and selecting ap- propriate learning algorithms, we aim to achieve accurate results. The CTU-13- Dataset, capturing diverse botnet examples, is utilized for experiments. Our re- search contributes to intrusion detection and botnet detection by emphasizing the importance of domain knowledge in feature engineering
Author: Vaishnavi Cherukuvada
Language: English
Subfield: Computer Networks and Communications
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W4409216616