Low severity3.7NVD Advisory· Published Mar 30, 2020· Updated Jun 17, 2026

CVE-2019-20634

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.

AI Insight

LLM-synthesized narrative grounded in this CVE's description and references.

Affected products

Proofpoint/Email Protection2 versions
cpe:2.3:a:proofpoint:email_protection:*:*:*:*:*:*:*:*+ 1 more
- cpe:2.3:a:proofpoint:email_protection:*:*:*:*:*:*:*:*range: <=2019-09-08
- (no CPE)range: <=2019-09-08
Proofpoint/Email Protectiondescription
Proofpoint/Proof-Puddingllm-create

Patches

Vulnerability mechanics

References

github.com/moohax/Talks/blob/master/slides/DerbyCon19.pdfnvdThird Party Advisory
www.proofpoint.com/us/security/CVE-2019-20634nvdVendor Advisory
www.proofpoint.com/us/security/security-advisories/pfpt-sn-2020-0001nvdVendor Advisory
atlas.mitre.org/studies/AML.CS0008nvd

News mentions

No linked articles in our index yet.

cvss	0.240
epss	0.001
exploit	0.000
kev	0.000
patch	0.000
ransomware	0.000