Aller au contenu
en Se connecter
6.2 Moyenne

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.

Produits et versions touchés

Produit Versions touchées Corrigé en
onnx 1.22 premières → < 1.22.0 1.22.0

Références

Chronologie

  1. Publiée
  2. Dernière modification

Autres CVE de onnx

Les 14 CVE de onnx →
CVE-2026-115921 Open Neural Network Exchange (ONNX) is an open standard for machine learning interoperability 6.2 Moyenne CVE-2026-115920 Open Neural Network Exchange (ONNX) is an open standard for machine learning interoperability 6.2 Moyenne CVE-2026-115919 Open Neural Network Exchange (ONNX) is an open standard for machine learning interoperability 6.2 Moyenne 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 Élevée
Suivre cette CVE