Skip to main content

NVIDIA Model-Optimizer EUVDEUVD-2026-94049

| CVE-2026-65142 HIGH
Deserialization of Untrusted Data (CWE-502)
2026-10-06 psirt@nvidia.com GHSA-4hxf-v5w4-4vm6
7.8
CVSS 3.1 · Vendor: nvidia
Share

Severity by source

Vendor (nvidia) PRIMARY
7.8 HIGH
AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
vuln.today AI
7.8 HIGH

Deserialization of a loaded model file: AV:L and UI:R because the victim must load the crafted artifact, PR:N as no prior auth is needed, with full C/I/A impact from code execution.

3.1 AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
4.0 AV:L/AC:L/AT:N/PR:N/UI:A/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N

Primary rating from Vendor (nvidia).

CVSS VectorVendor: nvidia

Attack Vector
Local
Attack Complexity
Low
Privileges Required
None
User Interaction
Required
Scope
Unchanged
Confidentiality
High
Integrity
High
Availability
High

Lifecycle Timeline

2
Analysis Generated
Oct 06, 2026 - 22:33 vuln.today
CVE Published
Oct 06, 2026 - 22:17 cve.org
HIGH 7.8

DescriptionCVE.org

NVIDIA Model-Optimizer contains a vulnerability where an attacker may cause deserialization of untrusted data. A successful exploit of this vulnerability might lead to code execution, data tampering, denial of service, and information disclosure.

AnalysisAI

Deserialization of untrusted data in NVIDIA Model-Optimizer (CVSS 3.1 base score 7.8) allows an attacker who supplies a crafted model artifact to achieve code execution, data tampering, denial of service, and information disclosure on the machine that loads it. The assessed vector (AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H) shows the severity comes from full loss of confidentiality and integrity once the payload runs, but the attacker must first get the victim to open or deserialize the malicious artifact in a local processing environment, so there is no remote, zero-interaction path. …

Unlock full vulnerability intelligence

  • Risk assessment & exploitation conditions
  • Attack chain visualization
  • Remediation with exact patch versions
  • Threat intelligence from 22 sources
  • Personal watchlist & email alerts

No credit card · 7-day full trial

Attack ChainAIDerived

Hypothetical attack flow derived from CVE metadata

Access
technique details hidden
Delivery
technique details hidden
Exploit
technique details hidden
Execution
technique details hidden
Impact
technique details hidden

Vulnerability AssessmentAI

Exploitation Exploitation requires the victim to load or deserialize an attacker-supplied model artifact using NVIDIA Model-Optimizer - the UI:R metric confirms this mandatory user action, and AV:L confirms the malicious file must reach the local processing environment. … Additional conditions and limiting factors are described in the full assessment.
Risk Assessment This is a credible but not emergency-level priority. … Full risk analysis with EPSS, KEV, and SSVC signal comparison available after sign-in.
Exploit Scenario Full exploit scenario with step-by-step reproduction available after sign-in.
Remediation No vendor-released patch has been identified at time of analysis, so the immediate action is to reconcile the installed Model-Optimizer version against the NVIDIA Product Security advisory (https://github.com/NVIDIA/product-security/tree/main/2026/5903) and upgrade to the fixed release as soon as NVIDIA publishes it; track the NVD entry (https://nvd.nist.gov/vuln/detail/CVE-2026-65142) for updates. … Detailed patch versions, workarounds, and compensating controls in full report.

Recommended ActionAI

Within 24 hours, identify all systems and pipelines using NVIDIA Model-Optimizer and restrict the loading of model artifacts to trusted sources only; implement file scanning or allowlisting for model files. …

Sign in for detailed remediation steps and compensating controls.

Threat intelligence, references, and detailed analysis are available after sign-in.

More in Nvidia

View all
CVE-2017-14491 CRITICAL POC
9.8 Oct 04

Heap-based buffer overflow in dnsmasq before 2.78 allows remote attackers to cause a denial of service (crash) or execut

CVE-2018-3639 MEDIUM POC
5.5 May 22

Systems with microprocessors utilizing speculative execution and speculative execution of memory reads before the addres

CVE-2016-1741 CRITICAL POC
9.8 Mar 24

The NVIDIA driver in the Graphics Drivers subsystem in Apple OS X before 10.11.4 allows attackers to execute arbitrary c

CVE-2013-0109 HIGH POC
7.2 Apr 08

The NVIDIA driver before 307.78, and Release 310 before 311.00, in the NVIDIA Display Driver service on Windows does not

CVE-2019-5684 CRITICAL POC
10.0 Aug 06

NVIDIA Windows GPU Display Driver (all versions) contains a vulnerability in DirectX drivers, in which a specially craft

CVE-2026-24207 CRITICAL POC
9.8 May 20

Authentication bypass in NVIDIA Triton Inference Server allows unauthenticated remote attackers to reach protected funct

CVE-2019-5685 CRITICAL POC
9.8 Aug 06

NVIDIA Windows GPU Display Driver (all versions) contains a vulnerability in DirectX drivers, in which a specially craft

CVE-2025-23359 HIGH POC
8.3 Feb 12

NVIDIA Container Toolkit for Linux contains a Time-of-Check Time-of-Use (TOCTOU) vulnerability when used with default co

CVE-2016-8812 HIGH POC
8.8 Nov 08

For the NVIDIA Quadro, NVS, and GeForce products, NVIDIA GeForce Experience R340 before GFE 2.11.4.125 and R375 before G

CVE-2017-1000251 HIGH POC
8.0 Sep 12

The native Bluetooth stack in the Linux Kernel (BlueZ), starting at the Linux kernel version 2.6.32 and up to and includ

CVE-2016-1861 HIGH POC
7.8 Jun 19

The NVIDIA Graphics Drivers subsystem in Apple OS X before 10.11.5 allows attackers to execute arbitrary code in a privi

CVE-2024-0132 HIGH POC
8.3 Sep 26

NVIDIA Container Toolkit 1.16.1 or earlier contains a Time-of-check Time-of-Use (TOCTOU) vulnerability when used with de

Share

EUVD-2026-94049 vulnerability details – vuln.today

This site uses cookies essential for authentication and security. No tracking or analytics cookies are used. Privacy Policy