Open Access Open Access  Restricted Access Subscription Access

ZeroDayPulse – AI-Based Real-Time CVE Prediction System

JAYAPRAKASH P, Ms. HARI PRIYA S

Abstract


ZeroDayPulse is an AI-driven framework that aims to accelerate vulnerability triage by combining live CVE feeds, lightweight natural language processing (TF-IDF), and ensemble classification (Random Forest). The system automatically ingests CVE records from the National Vulnerability Database (NVD), extracts textual and categorical features (description, attack vector, privileges, etc.), and computes probabilistic severity estimates. Predictions are delivered through an interactive dashboard to help security teams prioritize patching and monitoring workflows. Using automated feature extraction and an ensemble classifier produces fast, explainable scores suitable for continuous integration into vulnerability management processes. The NVD is the canonical source of CVE data used in this work; its structured feeds make automated ingestion and reproducible experiments possible.


Full Text:

PDF

References


National Institute of Standards and Technology (NIST). National Vulnerability Database (NVD). https://nvd.nist.gov/

Mohamed, N. (2025). Artificial intelligence and machine learning in cybersecurity: A deep dive into state-of-the-art techniques and future paradigms. Knowledge and Information Systems, 67, 6969-7055. https://link.springer.com/article/10.1007/s10115-025-02429-y

Kia, A. N., et al. (2024). A cyber risk prediction model using common vulnerabilities and exposures (CVE) data. [Journal name]. https://www.sciencedirect.com/science/article/pii/S0957417423021012

Zenebe, A. (2022). Cyber Threat Intelligence Discovery using Machine Learning. (Master’s thesis). https://scholarworks.lib.csusb.edu/cgi/viewcontent.cgi?article=1436&context=ciima

Sierhieiev, Y., Paiuk, V., Nicheporuk, A., & Kwiecien, A. (2023). Detection and prediction of the vulnerabilities in software: Behavioral analysis with machine learning (BAML). CEUR Workshop Proceedings. https://ceur-ws.org/Vol-3736/paper18.pdf

P. Santos, et al. (2025). A systematic review of cyber threat intelligence (CTI): lifecycle, levels, and machine learning integration. https://pmc.ncbi.nlm.nih.gov/articles/PMC12300000/

Nguyen, V. & Kebande, V. (2024). Analysis and Prediction of Cyber-Threats using Machine Learning algorithms. (Master’s thesis, Lund University). https://lup.lub.lu.se/student-papers/record/9186430/file/9186432.pdf

Sarker, I. H., Kayes, A. S. M., Badsha, S., Alqahtani, H., Watters, P., & Ng, A. (2020). Cybersecurity data science: An overview from machine learning perspective. Journal of Big Data, 7, 1-29. (Access via journal)

Jada, I., et al. (2024). The impact of artificial intelligence on organisational cyber-security: A systematic literature review. (Elsevier). https://www.sciencedirect.com/science/article/pii/S2543925123000372

Adam, C., Bulut, M. F., Sow, D., Ocepek, S., Bedell, C., & Ngweta, L. (2022). Attack techniques and threat identification for vulnerabilities. arXiv. https://arxiv.org/abs/2206.11171


Refbacks

  • There are currently no refbacks.