Medium severity · published Oct 26, 2026
CVE-2026-115922
ONNX: Denial of service via unchecked expansion of packed sub-byte tensors in ONNX Python APIs
New
6.2
CVSS
0.1%
EPSS
No
On KEV
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.
CVSS vector
CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Attack vector
Local
Complexity
Low
Privileges
None
User interaction
None
Confidentiality
None
Integrity
None
Availability
High
Scope
Unchanged
Exploitation
Is it being used?
Exploit prediction (EPSS)0.1% · higher than 3% of CVEs
Exploited in the wildNo evidence yet
CISA KEVNot listed
Ransomware campaign useNot known
Affected products
Which versions
ON
onnx · onnx
< 1.22.0 · source: vendor
Affected product
ON
onnx
onnx
More from onnx
9.1
CVE-2026-28500
ONNX Untrusted Model Repository Warnings Suppressed by silent=True in onnx.hub.load() — Silent Supply-Chain Attack
9.1
CVE-2024-7776
A vulnerability in the `download_model` function of the onnx/onnx framework, before and including version 1.16.1, allows for arbitrary file overwrite due to inadequate prevention…
8.6
CVE-2026-34445
ONNX: Malicious ONNX models can crash servers by exploiting unprotected object settings.
7.5
CVE-2026-27489
ONNX: Path Traversal via Symlink
7.1
CVE-2026-49114
ONNX symlink-following and path-traversal arbitrary file write