// For flags

CVE-2025-23335

 

Severity Score

4.4
*CVSS v3.1

Exploit Likelihood

*EPSS

Affected Versions

*CPE

Public Exploits

0
*Multiple Sources

Exploited in Wild

-
*KEV

Decision

Track
*SSVC
Descriptions

NVIDIA Triton Inference Server for Windows and Linux and the Tensor RT backend contain a vulnerability where an attacker could cause an underflow by a specific model configuration and a specific input. A successful exploit of this vulnerability might lead to denial of service.

NVIDIA Triton Inference Server para Windows y Linux, así como el backend de Tensor RT, presentan una vulnerabilidad que permite a un atacante causar un subdesbordamiento mediante una configuración de modelo específica y una entrada específica. Una explotación exitosa de esta vulnerabilidad podría provocar una denegación de servicio.

*Credits: N/A
CVSS Scores
Attack Vector
Network
Attack Complexity
High
Privileges Required
High
User Interaction
None
Scope
Unchanged
Confidentiality
None
Integrity
None
Availability
High
Attack Vector
Network
Attack Complexity
High
Authentication
Multiple
Confidentiality
None
Integrity
None
Availability
Complete
* Common Vulnerability Scoring System
SSVC
  • Decision:Track
Exploitation
None
Automatable
No
Tech. Impact
Partial
* Organization's Worst-case Scenario
Timeline
  • 2025-01-14 CVE Reserved
  • 2025-08-06 CVE Published
  • 2025-08-06 CVE Updated
  • 2025-08-13 EPSS Updated
  • ---------- Exploited in Wild
  • ---------- KEV Due Date
  • ---------- First Exploit
CWE
  • CWE-191: Integer Underflow (Wrap or Wraparound)
CAPEC
Affected Vendors, Products, and Versions
Vendor Product Version Other Status
Vendor Product Version Other Status <-- --> Vendor Product Version Other Status
NVIDIA
Search vendor "NVIDIA"
 Triton Inference Server
Search vendor "NVIDIA" for product "Triton Inference Server"
 25.05
Search vendor "NVIDIA" for product "Triton Inference Server" and version "25.05"
en
Affected