Spam-filter evasion via exposed MLX scores
Published Mar 30, 2020 · Updated Oct 28, 2024
Model extraction in all Proofpoint Email Protection versions allows remote attackers to infer spam-scoring behavior through returned email headers. The MLX engine exposes its interim mlxlogscore value in X-Proofpoint-Spam-Details headers, enabling repeated samples to train a copy-cat classifier. Exploitation requires downstream bounce messages that preserve those headers, no active rule updates, and MLX-only spam detection; it improves spam scores but does not bypass malware scanning.
Summary
What happened
Model extraction in all Proofpoint Email Protection versions allows remote attackers to infer spam-scoring behavior through returned email headers. The MLX engine exposes its interim mlxlogscore value in X-Proofpoint-Spam-Details headers, enabling repeated samples to train a copy-cat classifier. Exploitation requires downstream bounce messages that preserve those headers, no active rule updates, and MLX-only spam detection; it improves spam scores but does not bypass malware scanning.
The record
- CVE
- CVE-2019-20634
- Published
- Mar 30, 2020
- Updated
- Oct 28, 2024
- Vendor
- Unknown vendor
- Product
- Unknown product
- Classifications
- CWE-697
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Mar 30, 2020CVE publishedPublication date reported by the CVE source.
- Oct 28, 2024Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
What conditions does exploitation require?
What is affected?
Affected products and versions are unavailable in this record.
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- Proof Pudding copy-cat modelproof of concept · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo