CVE-2025-23335

Medium

Description

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.

SeverityMedium
CVSS4.4
Exploit probability—
ProductNvidia Triton Inference Server
PublishedAug 6, 2025
First seenAug 6, 2025
Weakness typeCWE-191CWE-191

How to fix

Update
  • nvidia triton_inference_server25.05 or later

Affected products

ProductAffected versionsFixed in
nvidia triton_inference_serverv < 25.0525.05

Check your version

Choose the product and enter the version you run to see whether it falls in the affected range.

In the Intelligence 360 plan

Attack Surface Management

See the assets tied to your domains, the technologies they run and known vulnerabilities in one list.