The Exploit Prediction Scoring System (EPSS) is an open, data-driven effort for predicting when software vulnerabilities will be exploited. Our goal is to assist network defenders to better prioritize vulnerability remediation efforts. While other industry standards have been useful for capturing innate characteristics of a vulnerability and provide measures of severity, they are limited in their ability to assess threat. EPSS fills that gap because it uses current threat information from CVE and real-world exploit data. The EPSS model produces a probability score between 0 and 1 (0 and 100%). The higher the score, the greater the probability that a vulnerability will be exploited.
We currently produce EPSS scores for all CVEs since January 1, 2017 -- over 60,000 vulnerabilities. In addition, the EPSS SIG is working to improve the maturity of data collection and analysis in order to provide near-real time assessments of all publicly disclosed vulnerabilities. This requires developing partnerships with data providers and establishing an infrastructure from which we can provide a publicly-accessible interface for EPSS scores. We are already ingesting multiple open and commercial datasets, and our most critical data are those that can identify instances of actual vulnerability exploitation (i.e. exploits in the wild), which can come from many sources: intrusion detection systems, honeypots, network observatories, malware analysis and detection efforts, and other sensor networks.
If you know of any potential data that could improve this effort, please let us know! We can be reached at epps-chairs at first.org.
In addition, if you would like to join the EPSS special interest group, send us an email at epss-chairs at first.org. Anyone is welcome to join our mailing list, and Slack. We meet every other Friday at 11 am eastern time.