Silent output corruption via miscomputed pooling offsets
Published Sep 25, 2025 · Updated Sep 25, 2025
Incorrect calculation in PyTorch 2.6.0 allows context-dependent attackers to induce wrong FractionalMaxPool2d output through torch.compile. The Inductor lowering reads random samples from the wrong dimension and uses floor instead of truncation when computing pooling offsets. Reachability requires compiled execution of the affected layer, and the bounded consequence is silently incorrect tensor output that can taint downstream model decisions.
Summary
What happened
Incorrect calculation in PyTorch 2.6.0 allows context-dependent attackers to induce wrong FractionalMaxPool2d output through torch.compile. The Inductor lowering reads random samples from the wrong dimension and uses floor instead of truncation when computing pooling offsets. Reachability requires compiled execution of the affected layer, and the bounded consequence is silently incorrect tensor output that can taint downstream model decisions.
The record
- CVE
- CVE-2025-46150
- Published
- Sep 25, 2025
- Updated
- Sep 25, 2025
- Vendor
- Unknown vendor
- Product
- Unknown product
- Classifications
- Unavailable
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Sep 25, 2025CVE publishedPublication date reported by the CVE source.
- Sep 25, 2025Record 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
No sourced classifications are available.
Public exploit references
- FractionalMaxPool2d torch.compile reproducerproof 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