CVE

CVE-2023-31036

What is CVE-2023-31036?

A vulnerability exists in NVIDIA Triton Inference Server for both Linux and Windows platforms, triggered when the server is started with the non-default command line parameter --model-control explicit. This condition enables an attacker to exploit the model load API, potentially allowing them to perform a relative path traversal. Exploitation of this issue may result in unauthorized code execution, denial of service, privilege escalation, and the possibility of unauthorized access to sensitive information or manipulation of data.

References