NVIDIA Triton Inference Server Memory Corruption Vulnerability in Python Backend

A memory corruption vulnerability has been identified in NVIDIA Triton Inference Server for Windows and Linux. This issue arises from the Python backend's shared memory region, which an attacker could access and manipulate. Exploiting this vulnerability may lead to a denial-of-service condition.

Impact

Exploitation of this vulnerability could cause memory corruption, potentially leading to a denial-of-service condition.

Remediation

Users are advised to update to version 25.08 of NVIDIA Triton Inference Server. The latest release can be downloaded from the Triton Inference Server Releases page on GitHub.