Lucene search
+L
Catalog
Vendors
Products
Timeline
Vulnerabilities
Sources
Documentation
Blog
Glossary
FAQ
Brand assets
Assessment
Agents dashboard
Agent Scanning
API Scanning
Assessment API
Alerts
Email notifications
Webhook notifications
Alerts API
SBOM package analysis
API Reference
Settings
Sign in

Security Bulletin: NVIDIA Triton Inference Server - April 2026

🗓️ 07 Apr 2026 00:00:00Reported by NvidiaType 
nvidia
 nvidia🔗 nvidia.custhelp.com👁 93 Views

Upgrade NVIDIA Triton Inference Server to r26.02 or later to fix denial of service vulnerabilities.

Related
Detection
ReporterTitlePublishedViews
Family
attackerkb
ATTACKERKB		CVE-2026-24175
7 Apr 202617:13
–attackerkb
attackerkb
ATTACKERKB		CVE-2026-24146
7 Apr 202617:11
–attackerkb
attackerkb
ATTACKERKB		CVE-2026-24174
7 Apr 202617:12
–attackerkb
attackerkb
ATTACKERKB		CVE-2026-24173
7 Apr 202617:12
–attackerkb
attackerkb
ATTACKERKB		CVE-2026-24147
7 Apr 202617:12
–attackerkb
bdu_fstec
BDU FSTEC		The software for deploying and executing AI models by NVIDIA Triton Inference Server is vulnerable, allowing attackers to trigger a service failure.
8 Apr 202600:00
–bdu_fstec
bdu_fstec
BDU FSTEC		The software for deploying and executing AI models in NVIDIA Triton Inference Server is vulnerable due to incorrect conversion of numerical value types. This vulnerability allows attackers to trigger service failures.
9 Apr 202600:00
–bdu_fstec
bdu_fstec
BDU FSTEC		The software for deploying and executing AI models by NVIDIA Triton Inference Server has vulnerabilities related to integer overflow. This allows attackers to trigger a service failure.
9 Apr 202600:00
–bdu_fstec
bdu_fstec
BDU FSTEC		The vulnerability of the software for deploying and executing AI models developed by NVIDIA Triton Inference Server (previously known as TensorRT Inference Server) relates to incorrect pathname restrictions. This vulnerability allows attackers to disclose sensitive information or cause service failures.
10 Jun 202600:00
–bdu_fstec
bdu_fstec
BDU FSTEC		The vulnerability of the software for deploying and executing AI models with NVIDIA Triton Inference Server (previously known as TensorRT Inference Server) involves uncontrolled memory consumption, which allows a malicious actor to cause service failures.
10 Jun 202600:00
–bdu_fstec
Rows per page
Vulners
Node
nvidiatriton_inference_serverRange<26.02

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

Book a live demo
07 Apr 2026 00:00Current
5.9Medium risk
Vulners AI Score5.9
CVSS 3.17.5
EPSS0.00528
SSVC
NVIDIA Triton Serversecurity updateversion upgradedenial of servicemalformed requestsinput validationr26.02 update
93