NVIDIA Triton Underflow Causes DoS via Model Config & Input
CVE-2025-23335 Published on August 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.

NVD

Vulnerability Analysis

CVE-2025-23335 can be exploited with network access, and requires user privileges. This vulnerability is consided to have a high level of attack complexity. The potential impact of an exploit of this vulnerability is considered to have no impact on confidentiality and integrity, and a high impact on availability.

Attack Vector:
NETWORK
Attack Complexity:
HIGH
Privileges Required:
HIGH
User Interaction:
NONE
Scope:
UNCHANGED
Confidentiality Impact:
NONE
Integrity Impact:
NONE
Availability Impact:
HIGH

Weakness Type

What is an Integer underflow Vulnerability?

The product subtracts one value from another, such that the result is less than the minimum allowable integer value, which produces a value that is not equal to the correct result. This can happen in signed and unsigned cases.

CVE-2025-23335 has been classified to as an Integer underflow vulnerability or weakness.


Products Associated with CVE-2025-23335

Want to know whenever a new CVE is published for NVIDIA Triton Inference Server? stack.watch will email you.

 

Affected Versions

NVIDIA Triton Inference Server Version All versions prior to 25.05 is affected by CVE-2025-23335

Exploit Probability

EPSS
0.06%
Percentile
17.96%

EPSS (Exploit Prediction Scoring System) scores estimate the probability that a vulnerability will be exploited in the wild within the next 30 days. The percentile shows you how this score compares to all other vulnerabilities.