CVE-2025-23335
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.
Does this matter?
High impact if exploited, but EPSS currently rates exploitation as unlikely (0.49%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.
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.
- CVSS 3.1
- 7.5 HIGHCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
- EPSS
- 0.49% probability · 41th percentile
- CISA KEV
- Not listed
- Weakness
- CWE-191
- Affected
- nvidia/triton inference server
- Source
- psirt@nvidia.com
References
- https://nvd.nist.gov/vuln/detail/CVE-2025-23335US Government Resource
- https://nvidia.custhelp.com/app/answers/detail/a_id/5687Vendor Advisory
- https://www.cve.org/CVERecord?id=CVE-2025-23335Third Party Advisory
Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.