ONNX: Denial of service via unchecked expansion of packed sub-byte tensors in ONNX Python APIs

影響: pip:onnx <= 1.21.0 → 1.22.0

ONNX's Python tensor-materialization helpers could allocate memory according to attacker-controlled tensor dimensions without verifying that a packed sub-byte payload contained the declared number of elements. A very small model could therefore cause a disproportionately large allocation when an application called onnx.numpy_helper.to_array() or constructed onnx.reference.ReferenceEvaluator with the model. The issue affected UINT2, INT2, UINT4, INT4, and FLOAT4E2M1 tensors stored in either raw_…

Read on GitHub Advisory Database

On 10/29/2026, 06:16 AM, GitHub Advisory Database published "ONNX: Denial of service via unchecked expansion of packed sub-byte tensors in ONNX Python APIs" (type: Advisory). Severity is "Medium" (medium). Related technologies: Python. CVE: CVE-2026-115922.