ONNX: Denial of service via unchecked expansion of packed sub-byte tensors in ONNX Python APIs
Summary
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_data or packed int32_data.
Technical details
The vulnerable _unpack_2bit() and _unpack_4bit() paths first allocated a small array based on the available packed bytes, then resized it to the shape declared in TensorProto.dims. They did not first confirm that the payload encoded enough logical elements for that shape.
For example, the reporter demonstrated a 66-byte model containing one packed byte and a declared dimension of 700,000,000. The model passed onnx.checker.check_model() and allocated approximately 700 MB while materializing the initializer, followed by another large allocation when executing the reference evaluator.
Loading, checking, or running shape inference on the serialized model alone did not trigger the allocation. The vulnerable tensor had to be materialized.
Impact
An application that materializes packed tensors from an untrusted model can exhaust available memory, causing denial of service. Memory corruption and code execution were not demonstrated.
Affected versions
- Affected: ONNX through 1.21.0
- Patched: ONNX 1.22.0
Remediation
Upgrade to ONNX 1.22.0 or later.
The primary fix validates the logical element count before resizing the unpacked NumPy array. A complementary checker change rejects an undersized packed payload before materialization.
- Materialization fix: onnx/onnx#8033
- Checker defense-in-depth: onnx/onnx#8038
The five affected tensor types and both storage formats were re-tested against the published ONNX 1.23.2 wheel and are rejected before the oversized allocation.
To verify the behavior using a released vulnerable package in an isolated environment, install onnx==1.21.0 with python -m pip install "onnx==1.21.0". Run memory-exhaustion demonstrations only with an appropriate process memory limit.
Severity
The vulnerable ONNX component processes the malicious model through a local library API or file boundary and is not itself bound to a network stack. Applications that expose ONNX model processing over a network should calculate an Environmental score with Modified Attack Vector set to Network.
Software afectado
Haz clic en una tecnología para ver todas sus vulnerabilidades.
| Plataforma | Paquete | Versiones vulnerables | Corregida en |
|---|---|---|---|
| Python (PyPI) | onnx | < 1.22.0 | 1.22.0 |
Referencias
- https://github.com/onnx/onnx/security/advisories/GHSA-q69g-f4f5-v8m7
- https://nvd.nist.gov/vuln/detail/CVE-2026-115922
- https://github.com/onnx/onnx/pull/8033
- https://github.com/onnx/onnx/pull/8038
- https://github.com/onnx/onnx/pull/8066
- https://github.com/onnx/onnx/commit/05c1bc3bceceb8d3cf11e9e7fc7f19f971c44988
- https://github.com/onnx/onnx/commit/8de2cf6aa47928e6515ac6d9e1a8b4758886a7df
- https://github.com/onnx/onnx/commit/dce5876d6cc6cc30157af7d26a752ef44976da8e
- https://github.com/onnx/onnx
- https://github.com/onnx/onnx/releases/tag/v1.22.0
- Vector CVSS
CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H- Debilidad (CWE)
CWE-789- Plataforma
- Python (PyPI)
- Paquete
onnx- Publicada
- 28.10.2026
- Actualizado
- 28.10.2026 23:17
Fuentes y licencias
OSV / GitHub Advisory Database - GHSA-q69g-f4f5-v8m7 - CC BY 4.0
Historial de vulnerabilidades: onnx
Todas las vulnerabilidades publicadas de este paquete (Python (PyPI)), de la más reciente a la más antigua. Muestra si es un fallo aislado o un paquete que hay que vigilar.
- Entradas en total
- 17
- Primera → última
- 01.2023 10.2026
- Sin corrección
- 0
- Explotada en ataques
- 0
Distribución por gravedad
- Crítica 1
- Alta 7
- Media 8
- Baja 1
Divulgaciones por año
- 2023: 1
- 2024: 3
- 2025: 1
- 2026: 12
-
ONNX: Denial of service via unchecked expansion of packed sub-byte tensors in ONNX Python APIs esta entrada
Identifica las vulnerabilidades de tu aplicación
Con la integración de DockRay y el inventario de software activado, DockRay compara las versiones notificadas de los componentes con las vulnerabilidades conocidas y avisa de las coincidencias confirmadas. La cobertura depende de la tecnología compatible y de los avisos disponibles.