Medium severity4.4NVD Advisory· Published Aug 6, 2025· Updated Jun 17, 2026
CVE-2025-23335
CVE-2025-23335
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.
AI Insight
LLM-synthesized narrative grounded in this CVE's description and references.
Affected products
3cpe:2.3:a:nvidia:triton_inference_server:*:*:*:*:*:*:*:*+ 2 more
- cpe:2.3:a:nvidia:triton_inference_server:*:*:*:*:*:*:*:*range: <25.05
- (no CPE)
- (no CPE)range: All versions prior to 25.05
Patches
Vulnerability mechanics
References
3- nvidia.custhelp.com/app/answers/detail/a_id/5687nvdVendor Advisory
- www.cve.org/CVERecordnvdThird Party Advisory
- nvd.nist.gov/vuln/detail/CVE-2025-23335nvdUS Government Resource
News mentions
0No linked articles in our index yet.