AI-Driven Vulnerability Prioritization Using Exploitability and Software Dependency Data

Authors

  • Shirazi. H, Maneriker.P , Fujita.H Author

Keywords:

Vulnerability prioritization, artificial intelligence, software dependencies, exploitability, dependency graph, risk-based remediation, cybersecurity.

Abstract

Software systems increasingly depend on open-source and third-party components. A vulnerability in one dependency may affect many applications, yet security teams often have limited time to investigate and remediate every finding. Prioritization based only on technical severity can overlook whether a vulnerability is likely to be exploited, whether the affected component is actually used, and whether it is reachable in the deployed application.

This paper proposes an AI-driven vulnerability prioritization framework that combines exploitability indicators with software dependency data. The framework integrates vulnerability records, exploit prediction scores, known exploitation evidence, dependency relationships, and deployment context. A dependency graph represents relationships among applications, packages, and vulnerable components. A machine-learning model estimates exploitation-related risk, while graph-based context identifies vulnerabilities that affect important or reachable components. The resulting priority score supports remediation decisions by considering both threat likelihood and organizational exposure.

The proposed approach is designed to improve the ordering of vulnerability remediation tasks rather than replace security analysts or established scoring systems. Evaluation should compare the framework with severity-only and exploitability-only baselines using a temporally separated dataset. Metrics should include precision and recall among the highest-ranked vulnerabilities, average precision, ranking quality, and remediation workload. The paper also discusses data quality, model explainability, dependency uncertainty, and operational limitations.

References

. Jacobs, J., Romanosky, S., Edwards, B., Adjerid, I., & Roytman, M. (2021). Exploit Prediction Scoring System (EPSS). Digital Threats: Research and Practice, 2(3), Article 20, 1–17. https://doi.org/10.1145/3436242

2. Jacobs, J., Romanosky, S., Adjerid, I., & Baker, W. (2020). Improving vulnerability remediation through better exploit prediction. Journal of Cybersecurity, 6(1), tyaa015. https://doi.org/10.1093/cybsec/tyaa015

3. Bozorgi, M., Saul, L. K., Savage, S., & Voelker, G. M. (2010). Beyond heuristics: Learning to classify vulnerabilities and predict exploits. In Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 105–114). https://doi.org/10.1145/1835804.1835820

4. Allodi, L., & Massacci, F. (2014). Comparing vulnerability severity and exploits using case-control studies. ACM Transactions on Information and System Security, 17(1), Article 1. https://doi.org/10.1145/2630069

5. FIRST. (2023). Common Vulnerability Scoring System version 4.0: Specification document. https://www.first.org/cvss/v4.0/specification-document

6. FIRST. (2023). Common Vulnerability Scoring System version 4.0: User guide. https://www.first.org/cvss/v4.0/user-guide

7. Kausar, F., Batiste, L., Muallem, A., & Hussain, S. (2026). Integrated risk scoring and exploit prediction for cyber-physical power system vulnerabilities. Energy Informatics, 9, Article 32. https://doi.org/10.1186/s42162-026-00640-x

8. Parente, F. R., Rodrigues, E. B., & Mattos, C. L. C. (2025). FRAPE: A framework for risk assessment, prioritization and explainability of vulnerabilities in cybersecurity. Journal of Information Security and Applications, 89, Article 103971. https://doi.org/10.1016/j.jisa.2025.103971

9. Márquez, A. G., Varela-Vaca, Á. J., & Gómez López, M. T. (2024). Vulnerability impact analysis in software project dependencies based on satisfiability modulo theories (SMT). Computers & Security, 139, Article 103669. https://doi.org/10.1016/j.cose.2023.103669

10. Enhancing vulnerability prioritization: Data-driven exploit predictions with community-driven insights. (2023). In 2023 IEEE European Symposium on Security and Privacy Workshops (EuroS&PW). https://doi.org/10.1109/EuroSPW59978.2023.00027

Downloads

Published

30-01-2026

How to Cite

AI-Driven Vulnerability Prioritization Using Exploitability and Software Dependency Data . (2026). Innovative Journal of Computing, Security and Digital Technologies, 1(1), 29-40. https://ijcdst.in/index.php/about/article/view/10

Similar Articles

1-10 of 15

You may also start an advanced similarity search for this article.