Vulnerability in Onnx

CVE-2026-115922

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.

Published · last modified .

CVSS v3 metric

CVSS v3 base score 6.2 (Medium). Vector: CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H.

EPSS exploit prediction

No EPSS score from FIRST.org yet. New CVEs usually get one within a few days; no score means no signal yet, not low risk. How EPSS works.

Affected products

  • Onnx — versions < 1.22.0

Weakness classification (CWE)

References

Frequently asked questions

What is CVE-2026-115922?
CVE-2026-115922 is a medium-severity vulnerability in Onnx, classified under CWE-789. CVSS score: 6.2/10. Published 2026-10-26.
How severe is CVE-2026-115922?
Medium severity. CVSS v3 base score is 6.2 out of 10.