Cyber Resilience

CVE-2025-23335

Memory Safety in Nvidia Triton Inference Server ≤ 25.05

Memory Safety
Published
06 August 2025
Modified
17 June 2026
Patch / advisory
View advisory
CVSS Score v3.1 4.4
Click a component to see what it means
Raw vectorCVSS:3.1/AV:N/AC:H/PR:H/UI:N/S:U/C:N/I:N/A:H
EPSS Score 0.0049 40th percentile
Risk Priority 36 floored blend · peak EPSS

Summary

CVE-2025-23335 is a medium-severity Wrap or Wraparound (CWE-191) vulnerability in Nvidia Triton Inference Server. Its CVSS base score is 4.4 (Medium).

Operationally, exploitation aligns with the MITRE ATT&CK technique Exploitation for Privilege Escalation (T1068); ranked at the 40th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog.

The strongest mitigations our analysis identified map to SA-11 (Developer Testing and Evaluation) and SA-8 (Security and Privacy Engineering Principles) — see the control section below for these in your framework.

EU & UK References

Vulnerability Data

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…

more

to denial of service.

CWE(s)
CWE-191

Related Threats

MITRE ATT&CK Enterprise Techniques

T1068 Exploitation for Privilege Escalation Privilege Escalation
Adversaries may exploit software vulnerabilities in an attempt to elevate privileges.
attack.mitre.org →
T1190 Exploit Public-Facing Application Initial Access
Adversaries may attempt to exploit a weakness in an Internet-facing host or system to initially access a network.
attack.mitre.org →
T1203 Exploitation for Client Execution Execution
Adversaries may exploit software vulnerabilities in client applications to execute code.
attack.mitre.org →
T1210 Exploitation of Remote Services Lateral Movement
Adversaries may exploit remote services to gain unauthorized access to internal systems once inside of a network.
attack.mitre.org →
T1212 Exploitation for Credential Access Credential Access
Adversaries may exploit software vulnerabilities in an attempt to collect credentials.
attack.mitre.org →
Derived from this CVE’s CWE(s) via the direct CWE→ATT&CK cross-walk.

CVEs Like This One

CVE-2025-23310Same product: Linux Linux Kernel
CVE-2025-33202Same product: Linux Linux Kernel
CVE-2025-23317Same product: Linux Linux Kernel
CVE-2025-23326Same product: Linux Linux Kernel
CVE-2025-23311Same product: Linux Linux Kernel
CVE-2025-23333Same product: Linux Linux Kernel
CVE-2025-23334Same product: Linux Linux Kernel
CVE-2025-23327Same product: Linux Linux Kernel
CVE-2024-53880Same product: Linux Linux Kernel
CVE-2025-23324Same product: Linux Linux Kernel

Affected Assets

nvidia
triton inference server
≤ 25.05

Mitigating Controls

Mitigating Controls (NIST 800-53 r5) AI

SA-11 Developer Testing and Evaluation good match

Developer testing and static/dynamic analysis directly find integer underflow defects before code is released.

SA-8 Security and Privacy Engineering Principles partial match

Security engineering principles require use of safe arithmetic constructs or language features that structurally eliminate integer underflow during subtraction.

SI-10 Information Input Validation partial match

Input validation can reject or sanitize values that would cause a subtraction to underflow the representable range.

Mitigating Controls (NIST CSF 2.0) AI

Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.

PR.PS-06 full match
prevents

Secure SDLC practices directly prevent integer underflow defects via input validation, bounds checking, and static analysis.

ID.RA-01 partial match
prevents

Vulnerability scanning and code analysis can surface underflow flaws after they are introduced.

PR.PS-02 partial match
prevents

Routine patching can remediate known underflow bugs once they are discovered in deployed software.

Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI

Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.

A.8.29 Security testing in development and acceptance mostly match
finds

Security testing in development catches integer underflow defects before release.

A.8.25 Secure development life cycle partial match
prevents

Secure development lifecycle mandates input validation and arithmetic checks that prevent integer underflow.

A.8.26 Application security requirements partial match
prevents

Application security requirements include bounds checking and safe arithmetic to avoid underflow conditions.

A.8.27 Secure system architecture and engineering principles partial match
prevents

Secure architecture principles require defensive coding patterns that mitigate integer wraparound risks.

A.8.28 Secure coding partial match
prevents

Secure coding standards directly prescribe safe integer handling and overflow/underflow prevention.

References