CyberQuant: Converting Cyber Threat Telemetry into Explainable Financial Risk Using Monte Carlo Simulation and Budget Optimization
Security teams report risk as technical scores, while management must decide in financial terms. This paper presents CyberQuant, a platform that converts cyber threat telemetry into explainable financial risk and an optimized security investment plan. Vulnerability data (CVE, CVSS, patch age and exploit availability) is mapped through a business dependency graph that connects assets to services, revenue and downtime cost. A probabilistic risk engine models incident frequency with a Poisson process and loss magnitude with Triangular and Lognormal distributions, and 10,000 Monte Carlo simulations produce an Expected Annual Loss (EAL) and a 95% Value-at-Risk (VaR95) in rupees. A digital twin allows what-if testing of controls before money is spent, and a 0-1 integer programming optimizer (OR-Tools) selects the control portfolio that reduces the most financially important risk under a fixed budget, comparing maximum risk reduction, maximum ROSI and risk-appetite strategies. Every figure can be traced back to its inputs, and an assumption auditor flags synthetic or weak inputs instead of presenting false precision. The system is demonstrated on a labelled synthetic scenario based on the Smart India Hackathon 2026 problem statement SIH26105.
Authors
- Raj Kamesh Makwana
Institutions
- Savitribai Phule Pune University (IN)
Publication Details
- Journal
- Zenodo (CERN European Organization for Nuclear Research)
- Published
- 2026-11-19
- DOI
- https://doi.org/10.5281/zenodo.24376940
- Primary Topic
- Information and Cyber Security
- Type
- preprint