Exploring Cybersecurity Risks in Higher Education Environments with Machine Learning

Summary

Strang and Vajjhala (2024) applied unsupervised machine learning (t-SNE with radial and correspondence analysis) to hypertext data from US higher education websites (a sample of 848), which yielded over 4,000 potential cybersecurity indicators, in an exploratory comparative study of how universities can assess breach risk. A combined 'control' feature scored breach likelihood on a 1–3 scale and was the most useful feature for flagging potentially very high-risk components. No malware breaches were detected in the sample, but higher risk scores clustered in the central and upper parts of the t-SNE map.

Practical implication. Decision-makers in educational institutions can use website-based machine learning risk maps to target cybersecurity interventions, provided the outputs are verified through method and data triangulation.

The Problem

Universities hold sensitive data on large, decentralized websites but lack a practical way to screen those sites for cybersecurity breach risk.

The Methodology

Exploratory comparative study applying unsupervised machine learning (t-SNE, radial analysis, correspondence analysis) in Python to hypertext data scraped from about 848 U.S. higher education website records.

The Core Finding

Unsupervised machine learning (t-SNE with radial and correspondence analysis) applied to hypertext from about 848 US higher-education website records, containing over 4,000 potential indicators, scored breach likelihood on a 1–3 scale and flagged concentrations of higher-risk components; a combined control feature was the most useful risk signal.

The Citation

Strang, K. D., & Vajjhala, N. R. (2024). Exploring Cybersecurity Risks in Higher Education Environments with Machine Learning. In 2024 4th International Conference on Pervasive Computing and Social Networking (ICPCSN) (pp. 1–6). IEEE. https://doi.org/10.1109/ICPCSN62568.2024.00008 Copy APA

The summary, key findings, methods, implications and relevance notes on this page are this website’s own description of the paper, written from the published abstract and text. The official abstract and citation details are given further down.

The study in detail

What question does this paper answer?

How can universities assess their risk of a cybersecurity breach by analyzing hypertext data from their websites with unsupervised machine learning?

What did the study find, in detail?

Hypertext data (URLs, embedded XML and HTTP scripts) were extracted from about 848 records of U.S. higher education institution websites, containing over 4,000 potential cybersecurity indicators, and analyzed with t-SNE, radial analysis and correspondence analysis. A combined 'control' feature scored breach likelihood from 1 to 3; no malware breaches were found in the sample, but higher risk scores concentrated in parts of the visualization, and some links did not resolve to working sites.

Why does it matter?

Universities run open, complex and decentralized IT infrastructures that make them targets for phishing, ransomware, DDoS attacks and insider threats. The authors argue that website-based machine learning risk scoring lets decision-makers in educational institutions spot anomalies that may indicate cybercrime or impending attacks, while method and data triangulation are needed to verify the reliability and validity of machine learning outputs.

Methods and data

Standards, datasets and methods named in this study

• t-SNE (t-distributed stochastic neighbor embedding) Method
  The unsupervised method used to model breach-risk indicators.
  van der Maaten, L., & Hinton, G. (2008). Visualizing data using t-SNE. Journal of Machine Learning Research, 9, 2579–2605.

Definitions and key terms

t-SNE (t-distributed stochastic neighbor embedding)

A machine learning technique that reduces high-dimensional data to a lower-dimensional map by minimizing the Kullback-Leibler divergence between pairwise similarity distributions, keeping similar points close and dissimilar points apart. — as used in Strang & Vajjhala (2024)

Unsupervised machine learning

Machine learning that finds structure or patterns in data without a labeled outcome variable. — as used in Strang & Vajjhala (2024)

Data triangulation

Checking the reliability and validity of findings by comparing results across multiple methods or data sources. — as used in Strang & Vajjhala (2024)

All key terms across the publications →

Abstract

This paper uses unsupervised machine learning techniques (ML) to explore the risk of cybersecurity breaches or attacks in the higher education sector, including schools, universities, and support organizations. A large sample of higher education institutions (N=848) was analyzed by extracting hypertext data from the websites of educational institutions to identify links that may signal a future cybersecurity breach or attack. ML T-distributed Stochastic Neighbor Embedding (t-SNE) was used to train a model for identifying likely indicators of cybersecurity breach risks. The authors used additional techniques, including radial analysis and correspondence analysis, to visualize the cybersecurity breach signals in the data. In this way, decision-makers should be able to spot anomalies that indicate cybercrime activity or potential cyber-attacks. This paper also exposes the problems of using ML and how to use methods and data triangulation to check reliability and validity.

Abstract as published in 2024 4th International Conference on Pervasive Computing and Social Networking (ICPCSN).

Keywords: unsupervised machine learning; cybersecurity breaches; higher education sector; hypertext data analysis; t-distributed stochastic neighbor embedding; pervasive computing; cyber-attack indicators; radial analysis; correspondence analysis; anomaly detection; data triangulation

Limitations

• The sample focused on medium-sized universities; the authors recommend future research include large and small institutions to test whether the identified risks and indicators hold across institution types and sizes.
• Leveraging machine learning for cybersecurity raises challenges of data reliability and model validity, requiring rigorous verification of machine learning outputs.
• The authors call for refined feature selection, comparison with deep learning and ensemble methods, additional data such as network traffic and email patterns, and longitudinal studies.

Practical implications

• Decision-makers in educational institutions can use website-based machine learning risk scoring to spot anomalies that may indicate cybercrime or impending attacks, according to the authors.
• Universities applying machine learning to cybersecurity should verify the outputs through method and data triangulation, because the authors report challenges of data reliability and model validity.
• For researchers, the sample focused on medium-sized universities, and the authors recommend that future research include large and small institutions to test whether the identified risks and indicators hold across institution types and sizes.
• Researchers extending the approach should consider refined feature selection, comparison with deep learning and ensemble methods, additional data such as network traffic and email patterns, and longitudinal studies, as the authors call for.

Drawn from Strang & Vajjhala (2024), 2024 4th International Conference on Pervasive Computing and Social Networking (ICPCSN), pp. 1–6, IEEE.

When this research may be relevant

This article may be relevant to researchers studying cybersecurity risk assessment in universities and higher education, machine learning approaches to breach-risk indicators from public web data, unsupervised visual analytics for security, and the validation challenges of ML-based cyber risk scoring.

Research topics addressed: cybersecurity; higher education; universities; machine learning; unsupervised learning; t-SNE; cyber risk assessment; website security; anomaly detection; cybercrime; radial analysis; correspondence analysis; Python; United States

How to cite

APA 7

Strang, K. D., & Vajjhala, N. R. (2024). Exploring Cybersecurity Risks in Higher Education Environments with Machine Learning. In 2024 4th International Conference on Pervasive Computing and Social Networking (ICPCSN) (pp. 1–6). IEEE. https://doi.org/10.1109/ICPCSN62568.2024.00008Copy APA citation

MLA 9

Strang, Kenneth David, and Narasimha Rao Vajjhala. “Exploring Cybersecurity Risks in Higher Education Environments with Machine Learning.” 2024 4th International Conference on Pervasive Computing and Social Networking (ICPCSN), IEEE, 2024, pp. 1–6. https://doi.org/10.1109/ICPCSN62568.2024.00008.Copy MLA citation

IEEE

K. D. Strang and N. R. Vajjhala, “Exploring Cybersecurity Risks in Higher Education Environments with Machine Learning,” in 2024 4th International Conference on Pervasive Computing and Social Networking (ICPCSN), 2024, pp. 1–6, doi: 10.1109/ICPCSN62568.2024.00008.Copy IEEE citation

@inproceedings{strang2024cybersecurity,
  title = {Exploring Cybersecurity Risks in Higher Education Environments with Machine Learning},
  author = {Strang, Kenneth David and Vajjhala, Narasimha Rao},
  booktitle = {2024 4th International Conference on Pervasive Computing and Social Networking (ICPCSN)},
  pages = {1--6},
  year = {2024},
  publisher = {IEEE},
  doi = {10.1109/ICPCSN62568.2024.00008},
  url = {https://doi.org/10.1109/ICPCSN62568.2024.00008}
}

TY  - CPAPER
TI  - Exploring Cybersecurity Risks in Higher Education Environments with Machine Learning
AU  - Strang, Kenneth David
AU  - Vajjhala, Narasimha Rao
T2  - 2024 4th International Conference on Pervasive Computing and Social Networking (ICPCSN)
PY  - 2024
DA  - 2024/05/03
SP  - 1
EP  - 6
PB  - IEEE
DO  - 10.1109/ICPCSN62568.2024.00008
UR  - https://www.narasimharao.net/research/cybersecurity-risks-higher-education-machine-learning/
LA  - en
ER  - 

Links and files

• DOI: https://doi.org/10.1109/ICPCSN62568.2024.00008
• Publisher’s page: https://ieeexplore.ieee.org/document/10607755
• This page as text: https://www.narasimharao.net/research/cybersecurity-risks-higher-education-machine-learning/paper.md
• Permanent address of this page: https://www.narasimharao.net/research/cybersecurity-risks-higher-education-machine-learning/