Security Bulletin: NVIDIA Triton Inference Server - September 2025

🗓️ 16 Sep 2025 00:00:00Reported by NvidiaType

NVIDIA Triton Inference Server secures fixes for multiple CVEs; install latest release and read Secure Deployment Guide.

Reporter	Title	Published	Views	Family All 66
BDU FSTEC	The vulnerability of the software for deploying and executing AI models developed with NVIDIA Triton Inference Server (previously known as TensorRT Inference Server) allows a perpetrator to execute arbitrary code by failing to take measures to neutralize specific elements.	19 Sep 202500:00	–	bdu_fstec
BDU FSTEC	The vulnerability of the NVIDIA Triton Inference Server (previously known as TensorRT Inference Server) software for deploying and running artificial intelligence models lies in the fact that it involves writing beyond the buffer boundaries, allowing a malicious actor to trigger a service failure.	7 Nov 202500:00	–	bdu_fstec
BDU FSTEC	The vulnerability of the software for deploying and executing AI models developed with NVIDIA Triton Inference Server (previously known as TensorRT Inference Server) allows a malicious actor to trigger service failures due to insufficient input data validation.	7 Nov 202500:00	–	bdu_fstec
BDU FSTEC	The vulnerability of the software for deploying and executing NVIDIA Triton Inference Server (previously known as TensorRT Inference Server) relates to access control errors, which allow a malicious actor to trigger a service failure.	7 Nov 202500:00	–	bdu_fstec
Circl	CVE-2025-23268	17 Sep 202522:42	–	circl
Circl	CVE-2025-23316	17 Sep 202519:45	–	circl
Circl	CVE-2025-23328	17 Sep 202523:12	–	circl
Circl	CVE-2025-23329	18 Sep 202505:16	–	circl
Circl	CVE-2025-23336	17 Sep 202522:42	–	circl
CNNVD	NVIDIA Triton Inference Server 输入验证错误漏洞	17 Sep 202500:00	–	cnnvd