A Framework to Quantify the Probability of Future Cyber Loss Events
LEFSA estimates future cyber-loss probabilities from Defender telemetry, with XGBoost reaching 0.90 mean AUC across 23 organizations.
LEFSA reformulates Loss Event Frequency estimation as machine-level cyber loss event prediction plus hierarchical aggregation across infrastructure. It was tested on proprietary Managed Detection and Response telemetry from 23 organizations using Microsoft Defender for Endpoint. XGBoost produced the best results, with a mean ROC AUC of 0.90 and consistently low calibration error. The authors argue operational telemetry contains useful signal for probabilistic, organization-wide cyber risk estimates.
- LEFSA predicts machine-level cyber loss events, then aggregates them hierarchically.
- Evaluation used Defender for Endpoint telemetry from 23 organizations.
- XGBoost reached a mean ROC AUC of 0.90 with low calibration error.
- Dependencies between machines are included in infrastructure-level aggregation.
Full article170 words · extracted from arxiv.org · click to collapse
Cybersecurity risk quantification remains challenging due to limited operational data and difficulties in quantifying Loss Event Frequency (LEF). This paper introduces the Loss Event Frequency Security Analyser (LEFSA), a probabilistic framework that reformulates LEF estimation as machine-level Cyber Loss Event (CLE) prediction combined with hierarchical infrastructure-level aggregation. LEFSA estimates calibrated machine-level CLE probabilities from operational cybersecurity telemetry and aggregates them across infrastructure layers while accounting for machine-level dependencies. This provides a foundation for scalable, explainable, and operationally applicable cyber risk estimation at the level of machines, services, business processes, and the entire organization. The framework was evaluated using proprietary Managed Detection & Response telemetry from 23 organizations using Microsoft Defender for Endpoint. XGBoost achieved the strongest predictive performance, with a mean area under the receiver operating characteristic curve of 0.90 and consistently low calibration error across evaluation periods. The results demonstrate that operational cybersecurity telemetry contains substantial predictive information for future CLE occurrence, supporting probabilistic machine-level modeling and hierarchical aggregation as a promising foundation for quantitative, data-driven cyber risk management.
Text extracted automatically; images, tables and formatting may be missing. Original: https://arxiv.org/abs/2609.21717