CVE-2026-34445 HIGH

CVE-2026-34445: ONNX: Malicious ONNX models can crash servers by exploiting unprotected object settings.

Vendor Onnx
Product onnx
Weakness CWE-20 · Input validation
Published April 1, 2026
Last update April 1, 2026

CVSS base score

8.6/10
Attack vector Network
Attack complexity Low
Privileges required None
User interaction None
Confidentiality Low
Integrity Low

CVSS vector

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:H

What the vulnerability does

01Description

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.

Key dates

02Disclosure timeline

April 1, 2026 CVE published
April 1, 2026 Record updated