What is the CVSS score of CVE-2024-53880?

CVE-2024-53880 has a CVSS 3.1 base score of 4.9 (Medium). CVSS vector: CVSS:3.1/AV:N/AC:L/PR:H/UI:N/S:U/C:N/I:N/A:H. EPSS exploitation probability: 0.1%.

Which versions of Triton Inference Server are affected by CVE-2024-53880?

Organizations using NVIDIA Triton Inference Server should be aware of moderate risk from CVE-2024-53880, a integer overflow vulnerability rated CVSS 4.9.

How to fix or mitigate CVE-2024-53880?

During next maintenance window: Identify affected systems and apply vendor patches when convenient. Monitor vendor channels for patch availability.

Triton Inference Server CVE-2024-53880

MEDIUM

Integer Overflow or Wraparound (CWE-190)

2025-02-12 psirt@nvidia.com

Denial Of Service Integer Overflow Triton Inference Server Nvidia

4.9

CVSS 3.1

CVSS VectorNVD

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

Lifecycle Timeline

Analysis Generated

Mar 28, 2026 - 18:26 vuln.today

CVE Published

Feb 12, 2025 - 01:15 nvd

MEDIUM 4.9

DescriptionNVD

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.

AnalysisAI

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. Rated medium severity (CVSS 4.9), this vulnerability is remotely exploitable, low attack complexity. No vendor patch available.

Technical ContextAI

This vulnerability is classified as Integer Overflow (CWE-190), which allows attackers to cause unexpected behavior through arithmetic overflow. 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. Affected products include: Nvidia Triton Inference Server.

RemediationAI

No vendor patch is available at time of analysis. Monitor vendor advisories for updates. Validate arithmetic operations, use safe integer libraries, check bounds before allocation.