We use these services and cookies to improve your user experience. You may opt out if you wish, however, this may limit some features on this site.
Please see our statement on Data Privacy.
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.
Reserved 2025-01-14 | Published 2025-08-06 | Updated 2025-08-06 | Assigner nvidiaCWE-191 Integer Underflow (Wrap or Wraparound)
nvd.nist.gov/vuln/detail/CVE-2025-23335
www.cve.org/CVERecord?id=CVE-2025-23335
nvidia.custhelp.com/app/answers/detail/a_id/5687
Support options