CVE-2026-24206

NVIDIA Triton Inference Server contains a vulnerability where an attacker could cause an authentication bypass. A successful exploit of this vulnerability might lead to escalation of privileges, denial of service, or information disclosure...

CVE-2026-24206

NVIDIA Triton Inference Server contains a vulnerability where an attacker could cause an authentication bypass. A successful exploit of this vulnerability might lead to escalation of privileges, denial of service, or information disclosure...

PT-2026-42094

Name of the Vulnerable Software and Affected Versions NVIDIA Triton Inference Server affected versions not specified Description A path traversal issue exists in the software, which could allow an attacker to cause a denial of service. Path traversal is a flaw that allows an attacker to access...

PT-2026-42392

Name of the Vulnerable Software and Affected Versions NVIDIA RTX 50, 40, 30, and 20 series cards affected versions not specified NVIDIA GTX 16, 10, 900, and some GTX 700 cards affected versions not specified Description A use-after-free issue exists on Linux systems that could allow attackers to...

NVIDIA TRT-LLM 代码问题漏洞

NVIDIA TRT-LM is a high-performance inference framework developed by NVIDIA Corporation for optimizing the inference acceleration and deployment of large language models. NVIDIA TRT-LM has code-related vulnerabilities, including deserialization vulnerabilities and insecure serialization handles,...

PT-2026-42218

Name of the Vulnerable Software and Affected Versions NVIDIA BioNeMo Core for Linux affected versions not specified Description A path traversal issue exists when loading a malicious file. This flaw allows a user to access files or directories outside the intended folder, which could lead to code...

NVIDIA TRT-LLM 安全漏洞

NVIDIA TRT-LM is a high-performance inference framework developed by NVIDIA Corporation for optimizing the inference acceleration and deployment of large language models. NVIDIA TRT-LM contains a security vulnerability, which stems from unchecked return values leading to null pointer dereferencin...

NVIDIA Triton Inference Server 输入验证错误漏洞

NVIDIA Triton Inference Server is an open-source software developed by NVIDIA Corporation. It helps standardize model deployment and provide fast, scalable AI in production environments. NVIDIA Triton Inference Server has a vulnerability related to input validation, which stems from integer...

NVIDIA Triton Inference Server 缓冲区错误漏洞

NVIDIA Triton Inference Server is an open-source software developed by NVIDIA Corporation. It helps standardize model deployment and provide fast, scalable AI in production environments. NVIDIA Triton Inference Server has a buffer error vulnerability, which stems from out-of-bounds reads in the...

PT-2026-42096

Name of the Vulnerable Software and Affected Versions NVIDIA Triton Inference Server affected versions not specified Description A flaw exists in the DALI backend that allows an attacker to trigger an out-of-bounds read, which occurs when a program reads data past the end of the intended buffer...

PT-2026-42089

Name of the Vulnerable Software and Affected Versions NVIDIA TRT-LLM affected versions not specified Description An issue exists where an unchecked return value can lead to a null pointer dereference, which occurs when a program attempts to read or write to a memory location using a pointer that ...

NVIDIA TensorRT 缓冲区错误漏洞

NVIDIA TensorRT is a software development toolkit provided by NVIDIA Corporation for the optimization of deep learning model inference and high-performance deployment. NVIDIA TensorRT has a buffer error vulnerability, which stems from out-of-bounds writes, potentially leading to data corruption...

PT-2026-42088

Name of the Vulnerable Software and Affected Versions NVIDIA TRT-LLM affected versions not specified Description NVIDIA TRT-LLM contains a deserialization issue and an unsafe serialized handle. Deserialization is the process of converting a data stream back into an object. A successful exploit...

PT-2026-42216

Name of the Vulnerable Software and Affected Versions NVIDIA TensorRT affected versions not specified Description An issue exists where an attacker could cause an out-of-bounds write, which is a condition where data is written outside the boundaries of a pre-allocated fixed-length block of memory...

PT-2026-42217

Name of the Vulnerable Software and Affected Versions NVIDIA BioNemo for Linux affected versions not specified Description An issue exists where a user can trigger the deserialization of untrusted data. Deserialization is the process of converting a data format, such as JSON or XML, back into an...

NVIDIA TRT-LLM 代码问题漏洞

NVIDIA TRT-LM is a high-performance inference framework developed by NVIDIA Corporation for optimizing the inference acceleration and deployment of large language models. NVIDIA TRT-LM has code-related vulnerabilities, which stem from insecure deserialization during RPC tests. These vulnerabiliti...

PT-2026-42095

Name of the Vulnerable Software and Affected Versions NVIDIA Triton Inference Server affected versions not specified Description An integer overflow can be triggered, which may lead to a denial of service. An integer overflow occurs when an arithmetic operation attempts to create a numeric value...

NVIDIA Triton Inference Server 安全漏洞

NVIDIA Triton Inference Server is an open-source software developed by NVIDIA Corporation. It helps standardize model deployment and provide fast, scalable AI in production environments. NVIDIA Triton Inference Server has a security vulnerability that stems from an authentication bypass. This...

PT-2026-42092

Name of the Vulnerable Software and Affected Versions NVIDIA Triton Inference Server versions prior to r26.03 Description An authentication bypass exists in the server that could allow an attacker to gain unauthorized access. Successful exploitation may result in code execution, escalation of...

NVIDIA Triton Inference Server 路径遍历漏洞

NVIDIA Triton Inference Server is an open-source software developed by NVIDIA Corporation. It helps standardize model deployment and provide fast, scalable AI in production environments. NVIDIA Triton Inference Server has a path traversal vulnerability, which stems from path traversal issues and...