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

published 2026-10-26 13 d ago modified 2026-10-30 9 d ago also GHSA-q69g-f4f5-v8m7 , EUVD-2026-110049

cvss: 6.2; version 3.1, CNA
cisa kev: Not listed; not in CISA's catalog
epss: 0.1%; EPSS 0.1% chance of exploitation in 30 days, percentile 2%
public exploits: 0; none known

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.

Patch / fix

fixed in 1 links 7

pypi onnx 1.22.0

github.com/onnx/onnx@05c1bc3 commit
github.com/onnx/onnx@8de2cf6 commit
github.com/onnx/onnx@dce5876 commit
github.com/onnx/onnx#8033 pull request
github.com/onnx/onnx#8038 pull request
github.com/onnx/onnx#8066 pull request
github.com/onnx/onnx/releases/tag/v1.22.0 release

Vendor advisories

What the vendors themselves say about their products: affected, fixed or not affected, and what to do.

red hat product security vex CVE-2026-115922 updated 2026-10-30 cvss 6.2

onnx: onnx: Denial of Service via excessive memory allocation in tensor unpacking

Red Hat OpenShift AI (RHOAI) rhoai/odh-mlserver-rhel9, rhoai/odh-mlserver-cuda-rhel9, rhoai/odh-openvino-model-server-rhel9, rhoai/odh-pipeline-runtime-pytorch-cuda-py312-rhel9, rhoai/odh-pipeline-runtime-pytorch-rocm-py312-rhel9, rhoai/odh-workbench-jupyter-pytorch-cuda-py312-rhel9, +11 more
affected: no fix available “Fix deferred”

Red Hat CSAF VEX © Red Hat, Inc., from https://security.access.redhat.com/data/csaf/v2/vex/; changed: reduced to product statuses and remediations. CC BY 4.0 · csaf

CISA SSVC

Exploitation: none
Automatable: no
Technical impact: partial
Assessed: 9 d ago (2026-10-30)

Exploit prediction

0.13% chance of exploitation in the next 30 days, higher than 2% of all scored CVEs (FIRST EPSS, 2026-11-08).

CVSS scores

assigned by	version	score	vector
CNA	3.1	6.2	CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
GitHub	3.1	6.2	CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

Affected packages

ecosystem	package	affected	fixed in
pypi	onnx	<1.22.0	1.22.0

Affected products

onnx onnx

Classification

Weakness

CWE-789 Memory Allocation with Excessive Size Value

References

Sources

Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.

Summary