Empirical Security Platform

Empirical Security Platform is an exposure management platform that uses machine learning models to produce calibrated probabilities of vulnerability exploitation, helping security teams prioritize remediation based on real-world exploitation data and environment-specific context. The platform operates two complementary predictive models: - Global Model: trained on approximately 2 million exploitation events from internet-scale data to forecast attacker behavior broadly - Local Model: trained on an organization's own assets, controls, patching cadence, network topology, and environmental telemetry to score vulnerabilities specific to that environment External data inputs include: - Monitoring of 17,000+ known exploited CVEs tracked in near-real time - Hourly exploitation telemetry per CVE with years of historical depth - Millions of malware hashes correlated to specific CVEs - 1,400+ OSINT sources - Ground-truth exploitation data from the team that built EPSS Local data inputs include scan results, asset metadata, compensating controls, patching velocity, and network topology. The local model improves incrementally with each additional month of data. Platform access is provided via three interfaces: - Web UI for exploring security data alongside known exploitation activity - REST API for retrieving the latest intelligence programmatically - AI Agent for automating triage, generating remediation plans, drafting exception requests, and surfacing emerging threats Key capabilities include toggling between local, global, and EPSS model views for any CVE, full transparency into the data features contributing to each score, and cross-referencing CVEs against real-time exploitation indicators such as active campaigns, malware associations, exploit maturity, and attacker infrastructure. Use cases supported: threat intelligence, vulnerability management, application security, and cloud security.