CVE-2026-34445

ONNX: Malicious ONNX models can crash servers by exploiting unprotected object settings.

State: Published
Severity: 8.6 High
Published: Apr 1, 2026
Updated: Apr 1, 2026
Reserved: Mar 27, 2026

Description

Open Neural Network Exchange (ONNX) is an open standard for machine learning interoperability. Prior to version 1.21.0, the ExternalDataInfo class in ONNX was using Python’s setattr() function to load metadata (like file paths or data lengths) directly from an ONNX model file. It didn’t check if the "keys" in the file were valid. Due to this, an attacker could craft a malicious model that overwrites internal object properties. This issue has been patched in version 1.21.0.

Scores

CVSS	Score	Vector	Source
3.1	8.6 High	CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:H	GitHub_M

Weaknesses

CWE-20 Improper Input Validation
CWE-400 Uncontrolled Resource Consumption
CWE-915 Improperly Controlled Modification of Dynamically-Determined Object Attributes

Affected Products

Product	Versions
onnxonnx	< 1.21.0Affected

References

Every record here comes from the CVE Program’s CVE List. © 1999–2026 The MITRE Corporation. CVE is a registered trademark of The MITRE Corporation. The records are reproduced under the CVE Program terms of use.