Will Pearce

**Name of the Vulnerable Software and Affected Versions** Proofpoint Email Protection versions prior to 2019-09-08 **Description** An issue was discovered in Proofpoint Email Protection. By collecting scores from Proofpoint email headers, it is possible to build a copy-cat Machine Learning Classification model and extract insights from this model. The insights gathered allow an attacker to craft emails that receive preferable scores, with a goal of delivering malicious emails. **Recommendations** For versions prior to 2019-09-08, consider implementing additional email filtering rules to detect and block malicious emails that may have been crafted using the insights gathered from the Proofpoint email headers. As a temporary workaround, consider enhancing the email scoring system to make it more difficult for attackers to build a copy-cat Machine Learning Classification model.