MEDIUM · 4.9

CVE-2024-53880

NVIDIA Triton Inference Server contains a vulnerability in the model loading API, where a user could cause an integer overflow or wraparound error by loading a model with an extra-large file size that...

Vulnerability Description

NVIDIA Triton Inference Server contains a vulnerability in the model loading API, where a user could cause an integer overflow or wraparound error by loading a model with an extra-large file size that overflows an internal variable. A successful exploit of this vulnerability might lead to denial of service.

CVSS Score

4.9

MEDIUM

CVSS:3.1/AV:N/AC:L/PR:H/UI:N/S:U/C:N/I:N/A:H
Attack Vector
NETWORK
Attack Complexity
LOW
Privileges Required
HIGH
User Interaction
NONE
Scope
UNCHANGED
Confidentiality
NONE
Integrity
NONE
Availability
HIGH

Affected Products

VendorProductVersions
NvidiaTriton Inference Server< 24.12
LinuxLinux Kernel-
MicrosoftWindows-

Related Weaknesses (CWE)

References

FAQ

What is CVE-2024-53880?

CVE-2024-53880 is a vulnerability with a CVSS score of 4.9 (MEDIUM). NVIDIA Triton Inference Server contains a vulnerability in the model loading API, where a user could cause an integer overflow or wraparound error by loading a model with an extra-large file size that...

How severe is CVE-2024-53880?

CVE-2024-53880 has been rated MEDIUM with a CVSS base score of 4.9/10. Review the CVSS metrics above for detailed severity breakdown.

Is there a patch for CVE-2024-53880?

Check the references section above for vendor advisories and patch information. Affected products include: Nvidia Triton Inference Server, Linux Linux Kernel, Microsoft Windows.