Cybersecurity

Cybersecurity Network Analysis

Network-based approaches are playing an increasingly vital role in securing modern cyber-physical systems. At SCADS, we apply the principles of graph theory, machine learning, and explainable AI to uncover, monitor, and mitigate threats in cyber environments. Our research combines rigorous algorithmic methods with real-world application in areas such as user authentication, intrusion detection, and critical infrastructure protection.

Generative Machine Learning for Cybersecurity

The future of cybersecurity is being shaped by advances in generative machine learning. Traditional machine learning models often struggle with limited labeled data and high false-positive rates in security contexts. At SCADS, we explore how generative models—such as GANs (Generative Adversarial Networks) and VAEs (Variational Autoencoders)—can alleviate these challenges by producing high-fidelity synthetic data to augment training and evaluation pipelines.

Generative models can serve dual purposes: enhancing detection accuracy and creating synthetic attack scenarios that improve model robustness under low-data or adversarial conditions. In particular, we study how these models can be applied to learn the distribution of benign network behavior and flag anomalous activity, thereby improving the effectiveness and generalizability of intrusion detection systems (IDS).

Cybersecurity Education

We study the state of cybersecurity education in the U.S. with a focus on workforce preparedness and curriculum alignment. Our work includes critical reviews of CAE-C designated programs, surveys of education research, and the design of hands-on learning experiences such as summer workshops. These efforts support national training initiatives and aim to strengthen the pipeline of work-ready cybersecurity professionals.

Papers

  • Halvorsen, Y. Yan, A. Gebremedhin, Denoising Diffusion Implicit Models for Generating Cyber Defense Network Traffic, IEEE International Conference on Communications (ICC), 2025.
    Abstract    Paper in PDF
  • J. Halvorsen, C. Izurieta, H. Cai, A. Gebremedhin, Applying Generative Machine Learning to Intrusion Detection: A Systematic Mapping Study and Review, ACM Computing Surveys, Volume 56, Issue 10, Article No. 257, 2024.
    Abstract    Paper in PDF
  • J. Halvorsen, A. Gebremedhin, Generative Machine Learning for Cyber Security, Military Cyber Affairs, Vol 7, Iss. 1, Article 4, 2024.
    Abstract    Paper in PDF
  • J. Crabb, C. Hundhausen, A. Gebremedhin, A Critical Review of Cybersecurity Education in the United States, ACM Technical Symposium on Computer Science Education (SIGCSE), 2024.
    Abstract    Paper in PDF
  • J. Crabb, C. Izurieta, B. Van Wie, O. Adesope, A. Gebremedhin, Cybersecurity Education: Insights From A Novel Cybersecurity Summer Workshop, IEEE Security & Privacy, Vol 22, pp. 89–98, Nov–Dec 2024.
    Abstract    Paper in PDF
  • J. Crabb, A. Gebremedhin, Cybersecurity Education and Research: Experiences in Training the Next Generation of Cyber Professionals, CYBER Magazine, MCPA, May 2024.
    Abstract    Paper in PDF
  • L. Wang, J. Halvorsen, S. Pannala, A. Srivastava, A. Gebremedhin, N. Schulz, CPSyNet: A Tool for Generating Customized Cyber-Power Synthetic Network for Distribution System with Distributed Energy Resources, IET Smart Grid, Vol 5, No 6, pp. 463–477, 2022.
    Abstract    Paper in PDF