94 matches found
CVE-2025-23320
NVIDIA Triton Inference Server for Windows and Linux contains a vulnerability in the Python backend, where an attacker could cause the shared memory limit to be exceeded by sending a very large request. A successful exploit of this vulnerability might lead to information disclosure...
CVE-2025-23334
CVE-2025-23334 concerns NVIDIA Triton Inference Server (Windows/Linux) with a Python backend flaw that allows an attacker to trigger an out-of-bounds read via a request, potentially leading to information disclosure. Connected advisories/records confirm this is a real vulnerability affecting Trit...
CVE-2025-23334
NVIDIA Triton Inference Server for Windows and Linux contains a vulnerability in the Python backend, where an attacker could cause an out-of-bounds read by sending a request. A successful exploit of this vulnerability might lead to information disclosure...
CVE-2025-23334
NVIDIA Triton Inference Server for Windows and Linux contains a vulnerability in the Python backend, where an attacker could cause an out-of-bounds read by sending a request. A successful exploit of this vulnerability might lead to information disclosure...
CVE-2025-23333
CVE-2025-23333 is acknowledged in NVIDIA’s security bulletin as a vulnerability in the Python backend of the Triton Inference Server for Windows and Linux. The issue allows an attacker to perform an out-of-bounds read by manipulating shared memory data, with information disclosure as the stated i...
CVE-2025-23333
NVIDIA Triton Inference Server for Windows and Linux contains a vulnerability in the Python backend, where an attacker could cause an out-of-bounds read by manipulating shared memory data. A successful exploit of this vulnerability might lead to information disclosure...
CVE-2025-23333
NVIDIA Triton Inference Server for Windows and Linux contains a vulnerability in the Python backend, where an attacker could cause an out-of-bounds read by manipulating shared memory data. A successful exploit of this vulnerability might lead to information disclosure...
CVE-2025-23320
NVIDIA Triton Inference Server for Windows and Linux contains a vulnerability in the Python backend, where an attacker could cause the shared memory limit to be exceeded by sending a very large request. A successful exploit of this vulnerability might lead to information disclosure...
CVE-2025-23320
CVE-2025-23320 affects the NVIDIA Triton Inference Server for Windows and Linux, with a vulnerability in the Python backend that could let an attacker send a very large request to exceed the shared memory limit and potentially disclose information. Affected component: Python backend processing of...
CVE-2025-23320
NVIDIA Triton Inference Server for Windows and Linux contains a vulnerability in the Python backend, where an attacker could cause the shared memory limit to be exceeded by sending a very large request. A successful exploit of this vulnerability might lead to information disclosure...
CVE-2025-23319
CVE-2025-23319 affects NVIDIA Triton Inference Server for Windows and Linux, specifically the Python backend. The vulnerability is an out-of-bounds write to memory buffer data that can be triggered by a crafted HTTP request. Successful exploitation could allow remote code execution, denial of ser...
CVE-2025-23318
NVIDIA Triton Inference Server for Windows and Linux contains a vulnerability in the Python backend, where an attacker could cause an out-of-bounds write. A successful exploit of this vulnerability might lead to code execution, denial of service, data tampering, and information disclosure...
CVE-2025-23318
NVIDIA Triton Inference Server for Windows and Linux contains a vulnerability in the Python backend, where an attacker could cause an out-of-bounds write. A successful exploit of this vulnerability might lead to code execution, denial of service, data tampering, and information disclosure...
CVE-2025-23320: Generation of Error Message Containing Sensitive Information
NVIDIA Triton Inference Server for Windows and Linux contains a vulnerability in the Python backend, where an attacker could cause the shared memory limit to be exceeded by sending a very large request. A successful exploit of this vulnerability might lead to information disclosure...
CVE-2025-23318: Buffer Access with Incorrect Length Value
NVIDIA Triton Inference Server for Windows and Linux contains a vulnerability in the Python backend, where an attacker could cause an out-of-bounds write. A successful exploit of this vulnerability might lead to code execution, denial of service, data tampering, and information disclosure...
NVIDIA Triton Inference Server 安全漏洞
Triton Inference Server is a high-performance inference service engine developed by NVIDIA, designed for AI model deployment in production environments, with support for a variety of frameworks TensorFlow, PyTorch, ONNX, etc. and optimized inference performance for GPUs and CPUs. An out-of-bounds...
CVE-2025-23319: Buffer Access with Incorrect Length Value
NVIDIA Triton Inference Server for Windows and Linux contains a vulnerability in the Python backend, where an attacker could cause an out-of-bounds write by sending a request. A successful exploit of this vulnerability might lead to remote code execution, denial of service, data tampering, or...
CVE-2025-23333: Out-of-bounds Read
NVIDIA Triton Inference Server for Windows and Linux contains a vulnerability in the Python backend, where an attacker could cause an out-of-bounds read by manipulating shared memory data. A successful exploit of this vulnerability might lead to information disclosure...
CVE-2025-23334: Out-of-bounds Read
NVIDIA Triton Inference Server for Windows and Linux contains a vulnerability in the Python backend, where an attacker could cause an out-of-bounds read by sending a request. A successful exploit of this vulnerability might lead to information disclosure...
NVIDIA Triton Bugs Let Unauthenticated Attackers Execute Code and Hijack AI Servers
A newly disclosed set of security flaws in NVIDIA's Triton Inference Server for Windows and Linux, an open-source platform for running artificial intelligence AI models at scale, could be exploited to take over susceptible servers. "When chained together, these flaws can potentially allow a remot...