CVE-2025-46150: In PyTorch before 2.7.0, when torch.compile is used, FractionalMaxPool2d has inconsistent results.
mediumvulnerability
security
Summary
CVE-2025-46150 is a bug in PyTorch (a machine learning framework) versions before 2.7.0 where FractionalMaxPool2d (a function that reduces image dimensions) produces inconsistent results when torch.compile (a performance optimization tool) is used. The issue causes the function to give different outputs under the same conditions, which is problematic for machine learning models that need reproducible, reliable results.
Solution / Mitigation
Upgrade to PyTorch version 2.7.0 or later.
Vulnerability Details
CVSS Score
5.3(medium)
EPSS (30-day exploit probability)
EPSS: 0.1%
Classification
Attack SophisticationModerate
Impact (CIA+S)
integrity
AI Component TargetedFramework
Affected Vendors
Original source: https://nvd.nist.gov/vuln/detail/CVE-2025-46150
First tracked: February 15, 2026 at 08:37 PM
Classified by LLM (prompt v3) · confidence: 85%