Security Bulletin: NVIDIA Triton Inference Server - August 2025

🗓️ 04 Aug 2025 00:00:00Reported by NvidiaType

NVIDIA Triton Inference Server update resolves critical vulnerabilities for effective system protection.

Reporter	Title	Published	Views	Family All 225
BDU FSTEC	The vulnerability of the software for deploying and executing AI models with NVIDIA Triton Inference Server (previously known as TensorRT Inference Server) relates to the execution of operations outside of the buffer in memory. This vulnerability allows a malicious actor to execute arbitrary code.	6 Aug 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 integer overflow. This vulnerability allows a malicious actor to trigger a service failure.	12 Aug 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 integer overflow. This vulnerability allows a malicious actor to trigger a service failure.	12 Aug 202500:00	–	bdu_fstec
BDU FSTEC	The vulnerability of the software for deploying and executing AI models developed by NVIDIA Triton Inference Server (previously known as TensorRT Inference Server) relates to buffer overflows in dynamic memory. This vulnerability allows attackers to cause system failures, gain unauthorized access to protected information, and execute arbitrary code.	12 Aug 202500:00	–	bdu_fstec
BDU FSTEC	The vulnerability of the software for deploying and executing NVIDIA Triton Inference Server (formerly TensorRT Inference Server) lies in its uncontrolled recursion. This allows a malicious actor to trigger a service failure.	12 Aug 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 integer overflow. This vulnerability allows a malicious actor to trigger a service failure.	12 Aug 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 a service failure. This vulnerability is related to zero-division errors.	12 Aug 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 integer overflow. This vulnerability allows a malicious actor to trigger a service failure.	12 Aug 202500:00	–	bdu_fstec
BDU FSTEC	The vulnerability of the software for deploying and executing AI models with NVIDIA Triton Inference Server (previously known as TensorRT Inference Server) relates to buffer overflows in the stack. This allows an attacker to gain unauthorized access to protected information, execute arbitrary code, or cause a service failure.	12 Aug 202500:00	–	bdu_fstec
BDU FSTEC	The vulnerability of the software for deploying and executing AI models with NVIDIA Triton Inference Server (previously known as TensorRT Inference Server) arises from the execution of operations beyond the buffer boundaries in memory. This allows attackers to gain unauthorized access to protected information, execute arbitrary code, or cause service failures.	12 Aug 202500:00	–	bdu_fstec