SA-26-113 Critical

NVIDIA Triton Inference Server: NVIDIA Triton Inference Server contains a vulnerability in the DALI backend where an attacker…

NVIDIA Triton Inference Server

Severity
Critical, CVSS 9.8
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Record
CVE-2026-24214
Affects
NVIDIA Triton Inference Server
Known exploited
Not listed in the CISA Known Exploited Vulnerabilities catalog
Published
Record first published by the source
May 20, 2026
Source last modified
July 24, 2026

Description

NVIDIA Triton Inference Server contains a vulnerability in the DALI backend where an attacker could cause an integer overflow. A successful exploit of this vulnerability might lead to code execution, data tampering, or denial of service.

Description quoted from the NVD record.

Who is affected

NVIDIA Triton Inference Server is software that runs AI models so that other programs can send them requests and get answers. This flaw is in a part of the server called the DALI backend, where an attacker could cause a number to grow too large for the space set aside for it (an integer overflow). If the attack succeeds, the attacker might run their own commands on the server, change data, or make the service stop working. No specific affected versions are named for this flaw. This flaw is rated Critical.

What to do

  1. If your organization runs NVIDIA Triton Inference Server itself, the person who installed or manages it should act on this advisory.
  2. No fixed version is named for this flaw yet, so check the vendor advisory linked on this page for a fixed release and install it as soon as it is available.
  3. If an IT provider or vendor runs the server for your organization, send them this advisory and ask when the update will be done.
  4. If you are not sure whether your organization uses this server, ask whoever looks after your computers or AI tools to check.

Analysis written from the source record as of July 24, 2026 and reviewed before publishing.

Sources

MORE ADVISORIES

See all