MediumVulnerability

CVE-2025-46150: PyTorch inconsistent results in FractionalMaxPool2d under torch.compile

Source: NVD(opens in a new tab)
Identifier: CVE-2025-46150
Published: September 25, 2025
Record updated: October 9, 2026

Known exploitation: Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
EPSS: 0.4%

Summary

CVE-2025-46150 affects PyTorch before 2.7.0. When torch.compile is used, FractionalMaxPool2d produces inconsistent results. NIST has not yet provided an NVD assessment, and the source lists no CVSS score.

Mitigation

The source does not state a fix yet. Check the original advisory for updates.

Details

Scores and exploitation

CVSS score: 5.3(medium)
EPSS: 0.4%Estimated probability that this CVE is exploited in the next 30 days, from the FIRST Exploit Prediction Scoring System. Read on November 4, 2026.

Classification

Attack sophistication: Moderate
AI component targeted: Framework
Impact: Integrity
Labels: security

How this record was produced

Summaries, mitigations and labels on this page are generated automatically from the source. The linked source is authoritative. The source gives this advisory a description and no title, so the title above is a headline generated from the source text.

Original source: https://nvd.nist.gov/vuln/detail/CVE-2025-46150

First tracked: February 15, 2026 at 08:37 PM ET, from NVD/CVE Database

Classifier: claude-haiku-5-5, prompt v4

Classifier confidence: 85% (self-assessed)