Skip to content
fr Sign in
6.2 Medium

CVE-2026-115922 Open Neural Network Exchange (ONNX) is an open standard for machine learning interoperability

Description

Open Neural Network Exchange (ONNX) is an open standard for machine learning interoperability. Prior to 1.22.0, _unpack_2bit() and _unpack_4bit() resize unpacked arrays according to attacker-controlled TensorProto.dims without verifying that raw_data or int32_data encodes the declared number of elements. Materializing an untrusted UINT2, INT2, UINT4, INT4, or FLOAT4E2M1 tensor through onnx.numpy_helper.to_array() or onnx.reference.ReferenceEvaluator can therefore expand a small packed payload into a disproportionately large allocation and exhaust memory. This issue is fixed in version 1.22.0.

Affected products and versions

Product Affected versions Fixed in
onnx 1.22 earliest → < 1.22.0 1.22.0

References

Timeline

  1. Published
  2. Last modified

Other CVEs of onnx

The 14 CVEs of onnx →
CVE-2026-115921 Open Neural Network Exchange (ONNX) is an open standard for machine learning interoperability 6.2 Medium CVE-2026-115920 Open Neural Network Exchange (ONNX) is an open standard for machine learning interoperability 6.2 Medium CVE-2026-115919 Open Neural Network Exchange (ONNX) is an open standard for machine learning interoperability 6.2 Medium CVE-2026-49114 In ONNX before 1.21.0, the 'save_external_data' function builds the external-data file path from the model's… 7.1 High
Track this CVE