NVIDIA Triton Inference Server for Windows and Linux and...
Moderate severity
Unreviewed
Published
Aug 6, 2025
to the GitHub Advisory Database
•
Updated Aug 6, 2025
Description
Published by the National Vulnerability Database
Aug 6, 2025
Published to the GitHub Advisory Database
Aug 6, 2025
Last updated
Aug 6, 2025
NVIDIA Triton Inference Server for Windows and Linux and the Tensor RT backend contain a vulnerability where an attacker could cause an underflow by a specific model configuration and a specific input. A successful exploit of this vulnerability might lead to denial of service.
References