PT-2025-39381 · Pytorch+1 · Pytorch+1

CVE-2025-46150

·

Published

2024-11-26

·

Updated

2025-10-05

CVSS v3.1

5.3

Medium

VectorAV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N
Name of the Vulnerable Software and Affected Versions PyTorch versions prior to 2.7.0
Description When torch.compile is used, the FractionalMaxPool2d function exhibits inconsistent results. This issue affects the accuracy of computations involving this specific function within the PyTorch framework. The FractionalMaxPool2d function is used for performing fractional max pooling operations, a common technique in deep learning models. The use of torch.compile introduces a performance optimization feature that, in this case, leads to the observed inconsistency.
Recommendations Update to PyTorch version 2.7.0 or later.

Exploit

Fix

Buffer Overflow

Found an issue in the description? Have something to add? Feel free to write us 👾

Weakness Enumeration

Related Identifiers

BDU:2025-13136
BIT-PYTORCH-2025-46150
CVE-2025-46150
ECHO-B465-9FDB-5EFB
PYSEC-2025-200

Affected Products

Debian
Pytorch