Empirical Security builds data-driven models for cybersecurity. The company maintains global models that track known exploited vulnerabilities and provides enterprise-specific local models. It was founded by the team behind Kenna Security, which was acquired by Cisco.
The company's best-known product is the Exploit Prediction Scoring System (EPSS), described as the world's only public machine learning model in cybersecurity. EPSS is used by over 120 vendors to score vulnerabilities. Empirical Security's global models track over 17,000 known exploited vulnerabilities, representing a 12.4x increase in total exploited CVEs tracked compared to CISA's Known Exploited Vulnerabilities catalogue. In the last 12 months, the models identified 4,925 newly exploited CVEs, compared with 204 added to the CISA KEV list in the same period.
Empirical Security's technical work spans machine learning, cybersecurity, and data-driven modelling. The company aims to build a security platform driven by modern AI and grounded in real-world telemetry, designed to make decisions rather than generate alerts.
