Memory Allocation Vulnerability in NVIDIA Triton Inference Server for Windows and Linux

CVE-2025-23331

What is CVE-2025-23331?

The NVIDIA Triton Inference Server, used on both Windows and Linux platforms, has a vulnerability that allows an attacker to send an invalid request with an excessively large memory allocation size. This can result in a segmentation fault, potentially leading to a denial of service. Users of Triton Inference Server should take precautions to mitigate this issue, as an exploit could disrupt service availability.

References