Lucene search
K

The software for deploying and executing AI models, NVIDIA Triton Inference Server (previously TensorRT Inference Server), is vulnerable due to synchronization errors when using a shared resource. This vulnerability allows attackers to cause service failures.

🗓️ 01 Jun 2026 00:00:00Reported by FSTEC of Russia — Information Security Threat DatabaseType 
bdu_fstec
 bdu_fstec
🔗 bdu.fstec.ru👁 1 Views

NVIDIA Triton Inference Server has synchronization errors with a shared resource, enabling remote service failures.

Related
Detection
Refs
ReporterTitlePublishedViews
Family
ATTACKERKB
CVE-2025-33254
24 Mar 202620:26
attackerkb
Circl
CVE-2025-33254
24 Mar 202622:01
circl
CNNVD
NVIDIA Triton Inference Server 竞争条件问题漏洞
24 Mar 202600:00
cnnvd
CVE
CVE-2025-33254
24 Mar 202620:26
cve
Cvelist
CVE-2025-33254
24 Mar 202620:26
cvelist
EUVD
EUVD-2025-208976
24 Mar 202621:31
euvd
NVD
CVE-2025-33254
24 Mar 202621:16
nvd
Nvidia
Security Bulletin: NVIDIA Triton Inference Server - March 2026
24 Mar 202600:00
nvidia
Positive Technologies
PT-2026-27507
24 Mar 202600:00
ptsecurity
RedhatCVE
CVE-2025-33254
26 Mar 202615:05
redhatcve
Rows per page
Vulners

Data

Build on a solid foundation with Vulners data

We provide the essential building blocks for cybersecurity solutions with comprehensive, structured, and constantly updated vulnerability and exploits data

Api

Power your application with Vulners API

The Vulners REST API offers reliable, high-performance access to vulnerability intelligence, with 99.9% SLA uptime and CDN-backed data delivery for seamless global access

App

Assess and manage vulnerabilities with Vulners tools

Built on top of Vulners' database and SDK, end-user solutions give security professionals and developers lightweight and powerful tools for vulnerability remediation

01 Jun 2026 00:00Current
5.7Medium risk
Vulners AI Score5.7
CVSS 37.5
CVSS 27.8
EPSS0.00323
1