Lucene search
K

The vulnerability of the software for deploying and executing AI models with NVIDIA Triton Inference Server (previously known as TensorRT Inference Server) lies in its uncontrolled memory allocation. This allows attackers to trigger service failures.

🗓️ 13 Aug 2025 00:00:00Reported by FSTEC of Russia — Information Security Threat DatabaseType 
bdu_fstec
 bdu_fstec
🔗 bdu.fstec.ru👁 1 Views

Uncontrolled memory allocation in NVIDIA Triton Inference Server can cause service failures.

Related
Detection
Refs
ReporterTitlePublishedViews
Family
Circl
CVE-2025-23331
6 Aug 202513:55
circl
CNNVD
NVIDIA Triton Inference Server 安全漏洞
6 Aug 202500:00
cnnvd
CNVD
NVIDIA Triton Inference Server Denial of Service Vulnerability
18 Aug 202500:00
cnvd
CVE
CVE-2025-23331
6 Aug 202512:42
cve
Cvelist
CVE-2025-23331
6 Aug 202512:42
cvelist
EUVD
EUVD-2025-23847
3 Oct 202520:07
euvd
NVD
CVE-2025-23331
6 Aug 202513:15
nvd
Nvidia
Security Bulletin: NVIDIA Triton Inference Server - August 2025
4 Aug 202500:00
nvidia
OSV
CVE-2025-23331
6 Aug 202513:15
osv
Positive Technologies
PT-2025-32167 · Nvidia · Nvidia Triton Inference Server
4 Aug 202500:00
ptsecurity
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

13 Aug 2025 00:00Current
5.8Medium risk
Vulners AI Score5.8
CVSS 37.5
CVSS 27.8
EPSS0.00519
1