CVE-2026-44512
published 2026-07-08CVE-2026-44512: Open Neural Network Exchange (ONNX) is an open standard for machine learning interoperability. From 1.9.0 before 1.22.0…
PriorityP420medium5.5CVSS 3.1
AVLACLPRNUIRSUCNINAH
EPSS
0.18%
8.2th percentile
Open Neural Network Exchange (ONNX) is an open standard for machine learning interoperability. From 1.9.0 before 1.22.0, onnx.version_converter.convert_version() can dereference a null pointer in Upsample_6_7::adapt_upsample_6_7() in onnx/version_converter/adapters/upsample_6_7.h when processing an untrusted model with an Upsample node that has zero inputs, causing an unrecoverable denial of service. This issue is fixed in version 1.22.0.
Affected
19 ranges
| Vendor | Product | Version range | Fixed in |
|---|---|---|---|
| linuxfoundation | onnx | >= 1.9.0 < 1.22.0 | 1.22.0 |
| onnx | onnx | — | — |
| onnx | onnx | >= 1.9.0 < 1.22.0 | 1.22.0 |
| rhoai | odh-mlserver-rhel9 | — | — |
| rhoai | odh-openvino-model-server-rhel9 | — | — |
| rhoai | odh-pipeline-runtime-datascience-cpu-py312-rhel9 | — | — |
| rhoai | odh-pipeline-runtime-pytorch-cuda-py312-rhel9 | — | — |
| rhoai | odh-pipeline-runtime-pytorch-llmcompressor-cuda-py312-rhel9 | — | — |
| rhoai | odh-pipeline-runtime-pytorch-rocm-py312-rhel9 | — | — |
| rhoai | odh-pipeline-runtime-tensorflow-cuda-py312-rhel9 | — | — |
| rhoai | odh-pipeline-runtime-tensorflow-rocm-py312-rhel9 | — | — |
| rhoai | odh-workbench-codeserver-datascience-cpu-py312-rhel9 | — | — |
| rhoai | odh-workbench-jupyter-datascience-cpu-py312-rhel9 | — | — |
| rhoai | odh-workbench-jupyter-pytorch-cuda-py312-rhel9 | — | — |
| rhoai | odh-workbench-jupyter-pytorch-llmcompressor-cuda-py312-rhel9 | — | — |
| rhoai | odh-workbench-jupyter-pytorch-rocm-py312-rhel9 | — | — |
| rhoai | odh-workbench-jupyter-tensorflow-cuda-py312-rhel9 | — | — |
| rhoai | odh-workbench-jupyter-tensorflow-rocm-py312-rhel9 | — | — |
| rhoai | odh-workbench-jupyter-trustyai-cpu-py312-rhel9 | — | — |
CVSS provenance
nvdv3.15.5MEDIUMCVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H
vendor_redhat5.5MEDIUM
Stop checking back — get the weekly exploitation signal.
Every Monday: what got weaponized or added to CISA KEV in the last seven days — each CVE cross-linked to its PoC, Nuclei template, and detection rule. Free, one email a week, unsubscribe in one click.
Red Hat
onnx: ONNX: Denial of Service via crafted untrusted models
vendor_redhat·2026-07-08·CVSS 5.5
CVE-2026-44512 [MEDIUM] CWE-476 onnx: ONNX: Denial of Service via crafted untrusted models
onnx: ONNX: Denial of Service via crafted untrusted models
Open Neural Network Exchange (ONNX) is an open standard for machine learning interoperability. From 1.9.0 before 1.22.0, onnx.version_converter.convert_version() can dereference a null pointer in Upsample_6_7::adapt_upsample_6_7() in onnx/version_converter/adapters/upsample_6_7.h when processing an untrusted model with an Upsample node that has zero inputs, causing an unrecoverable denial of service. This issue is fixed in version 1.22.0.
A flaw was found in Open Neural Network Exchange (ONNX), an open standard for machine learning interoperability. This vulnerability allows a remote attacker to cause an unrecoverable denial of service (DoS) by providing a specially crafted untrusted model. The flaw occurs when the onnx.version_c
VulDB
ONNX up to 1.21.0 Version Converter Adapters upsample_6_7.h adapt_upsample_6_7 inputs null pointer dereference (Nessus ID 326083)
vuldb·2026-07-13·CVSS 5.5
CVE-2026-44512 [MEDIUM] ONNX up to 1.21.0 Version Converter Adapters upsample_6_7.h adapt_upsample_6_7 inputs null pointer dereference (Nessus ID 326083)
A vulnerability labeled as problematic has been found in ONNX up to 1.21.0. Affected by this issue is the function Upsample_6_7::adapt_upsample_6_7 of the file onnx/version_converter/adapters/upsample_6_7.h of the component Version Converter Adapters. Executing a manipulation of the argument inputs can lead to null pointer dereference.
This vulnerability is registered as CVE-2026-44512. It is possible to launch the attack remotely. No exploit is available.
GHSA
ONNX has Null Pointer Dereference in Upsample Version Converter Adapter (Zero Inputs)
ghsa·2026-07-07
CVE-2026-44512 [MEDIUM] CWE-476 ONNX has Null Pointer Dereference in Upsample Version Converter Adapter (Zero Inputs)
ONNX has Null Pointer Dereference in Upsample Version Converter Adapter (Zero Inputs)
### Summary
Null pointer dereference (SIGSEGV) in `Upsample_6_7::adapt_upsample_6_7()` (`onnx/version_converter/adapters/upsample_6_7.h:31`) when `convert_version()` processes a model with an Upsample node that has zero inputs. The adapter accesses `node->inputs()[0]->sizes()` without checking input count. 107-byte PoC crashes on Release build.
This is the same class of bug as the Cast adapter advisory (separate report) but in a different adapter, different file, and different operator.
### Details
The Upsample 6→7 adapter validates attributes but not inputs:
```cpp
// upsample_6_7.h:20-33
void adapt_upsample_6_7(..., Node* node) const {
ONNX_ASSERTM(
node->hasAttribute(width_scale_symbol) && node->h
No detection rules found.
No public exploits indexed.
2026-07-08
Published