Description
An issue was discovered in Proofpoint Email Protection through 2019-09-08. 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.
References (5)
Core 5
Core References
Various Sources
https://atlas.mitre.org/studies/AML.CS0008
Third Party Advisory x_refsource_misc
https://github.com/moohax/Proof-Pudding
Third Party Advisory x_refsource_misc
https://github.com/moohax/Talks/blob/master/slides/DerbyCon19.pdf
Vendor Advisory x_refsource_confirm
https://www.proofpoint.com/us/security/CVE-2019-20634
Vendor Advisory x_refsource_misc
https://www.proofpoint.com/us/security/security-advisories/pfpt-sn-2020-0001
Scores
CVSS v3
3.7
EPSS
0.0158
EPSS Percentile
72.2%
Attack Vector
NETWORK
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:N/A:N
Details
CWE
CWE-697
Status
published
Products (1)
proofpoint/email_protection
< 2019-09-08
Published
Mar 30, 2020
Tracked Since
Feb 18, 2026