CVE-2026-34445
Open Neural Network Exchange (ONNX) is an open standard for machine learning interoperability.
Published Apr 1, 2026 · updated Jun 17, 2026 · linuxfoundation onnx
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.
Code
The project this record applies to. Exploit listings stay in References.
Timeline
Detection, updates, and resolution for this record.
Apr 1, 2026 · NIST NVD
Detected
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 overwrit
Jun 17, 2026 · NIST NVD
Updated
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 overwrit
Affected
- cpe linuxfoundation/onnxversion unspecified
Sources
- CVE.orgVulnerability recordCVE-2026-34445
Official CVE identifier
cve.org - NIST NVDVulnerability recordCVE-2026-34445
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
nvd.nist.gov