NVIDIA Triton Inference Server for Linux and Windows contains a vulnerability where, when it is launched with the non-default command line option --model-control explicit, an attacker may use the model load API to cause a relative path traversal. A successful exploit of this vulnerability may lead to code execution, denial of service, escalation of privileges, information disclosure, and data tampering.
History

No history.

cve-icon MITRE

Status: PUBLISHED

Assigner: nvidia

Published: 2024-01-12T17:11:38.579Z

Updated: 2024-08-02T14:45:25.650Z

Reserved: 2023-04-22T02:38:33.414Z

Link: CVE-2023-31036

cve-icon Vulnrichment

No data.

cve-icon NVD

Status : Analyzed

Published: 2024-01-12T17:15:09.183

Modified: 2024-01-18T20:45:53.087

Link: CVE-2023-31036

cve-icon Redhat

No data.