Every CVE Search/ Get API key

CVE-2025-23335

NVIDIA Triton Inference Server for Windows and Linux and the Tensor RT backend contain a...

4.4 Medium

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.

Attack profile

How easy it is to exploit

Attack vector
Network
Complexity
High
Privileges needed
High
User interaction
None

What an attacker can affect

Confidentiality
None
Integrity
None
Availability
High

Exploit likelihood

0.57%Up 0.5 points since Aug 7, 2025
90%50%10%1%

What each source reports

CVE List Score used 4.4

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.

Record
CVE-2025-23335
CVSS 3.1
4.4 MediumCVSS:3.1/AV:N/AC:H/PR:H/UI:N/S:U/C:N/I:N/A:H
Weakness
CWE-191
Updated
2026-11-02
EUVDEUVD-2025-23828 4.4

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.

Record
EUVD-2025-23828
CVSS 3.1
4.4 MediumCVSS:3.1/AV:N/AC:H/PR:H/UI:N/S:U/C:N/I:N/A:H
Updated
2026-11-02
GitHub AdvisoriesGHSA-r7f8-w95q-c4g4 4.4

NVIDIA Triton Inference Server for Windows and Linux and the Tensor RT backend contain a...

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.

Record
GHSA-r7f8-w95q-c4g4
CVSS 3.1
4.4 MediumCVSS:3.1/AV:N/AC:H/PR:H/UI:N/S:U/C:N/I:N/A:H
Weakness
CWE-191
Updated
2026-11-02
NVD 4.4

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.

Record
CVE-2025-23335
CVSS 3.1
4.4 MediumCVSS:3.1/AV:N/AC:H/PR:H/UI:N/S:U/C:N/I:N/A:H
CVSS 3.1
7.5 HighCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Weakness
CWE-191
Updated
2026-11-02

Affected products

History

History
RecordedChangedSources
first indexedCVE List, EUVD, GitHub Advisories, NVD

Dates are when Every CVE recorded each change. Upstream dates may differ.

In short

CVE-2025-23335 is a medium vulnerability (CVSS 4.4) in Nvidia Triton Inference Server, published August 6, 2025. No source lists public exploit code. EPSS puts the chance of exploitation in the next 30 days at 0.57%, the 47th percentile. No source names a fixed version.

References

MoveEnter Open