Skip to main content

ONNX CVE-2026-44512

| EUVDEUVD-2026-42355 MEDIUM
NULL Pointer Dereference (CWE-476)
2026-07-07 https://github.com/onnx/onnx GHSA-hwpq-hmq9-wj77
5.5
CVSS 3.1 · Vendor: https://github.com/onnx/onnx
Share

Severity by source

Vendor (https://github.com/onnx/onnx) PRIMARY
5.5 MEDIUM
AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H
vuln.today AI
5.5 MEDIUM

File-based local delivery with required user invocation of convert_version(); crash-only impact means C:N/I:N, PR:N because no credentials are needed to supply a file.

3.1 AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H
4.0 AV:L/AC:L/AT:N/PR:N/UI:A/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N

Primary rating from Vendor (https://github.com/onnx/onnx).

CVSS VectorVendor: https://github.com/onnx/onnx

CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H
Attack Vector
Local
Attack Complexity
Low
Privileges Required
None
User Interaction
Required
Scope
Unchanged
Confidentiality
None
Integrity
None
Availability
High

Lifecycle Timeline

1
Analysis Generated
Jul 07, 2026 - 13:43 vuln.today

Blast Radius

ecosystem impact
† from your stack dependencies † transitive graph · vuln.today resolves 4-path depth
  • 6 pypi packages depend on onnx (6 direct, 0 indirect)

Ecosystem-wide dependent count for version 1.9.0.

DescriptionCVE.org

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->hasAttribute(height_scale_symbol),
        "...")  // Attribute check PASSES

    auto width_scale = node->f(width_scale_symbol);
    auto height_scale = node->f(height_scale_symbol);

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

The PoC has an Upsample node at opset 6 with the required width_scale and height_scale 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 array_ref.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 version_converter

poc_b64 = "CAI6YQo8EgFZIghVcHNhbXBsZSoVCgt3aWR0aF9zY2FsZRUAAABAoAEBKhYKDGhlaWdodF9zY2FsZRUAAABAoAEBEgR0ZXN0YhsKAVkSFgoUCAESEAoCCAEKAggBCgIIBAoCCARCBAoAEAY="

model = onnx.load_from_string(base64.b64decode(poc_b64))
# CRASHES - Upsample_6_7 adapter dereferences empty inputs array
version_converter.convert_version(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.version_converter.convert_version() 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 (cast_9_8, softmax_12_13, softmax_13_12, upsample_6_7, upsample_9_10, group_normalization_20_21, broadcast_forward_compatibility, upsample_9_8) and all have been fixed in PR #7813.

AnalysisAI

Null pointer dereference in the ONNX Python library's version converter crashes any application that calls onnx.version_converter.convert_version() on a crafted model containing an Upsample node with zero inputs, producing an unrecoverable SIGSEGV. Affected versions include at minimum onnx 1.21.0 and 1.22.0, confirmed by a 107-byte public proof-of-concept; the vulnerability is part of a systemic pattern spanning eight adapters. …

Unlock full vulnerability intelligence

  • Risk assessment & exploitation conditions
  • Attack chain visualization
  • Remediation with exact patch versions
  • Threat intelligence from 22 sources
  • Personal watchlist & email alerts

Free forever · No credit card required

Attack ChainAIDerived

Hypothetical attack flow derived from CVE metadata

Access
Craft 107-byte ONNX model with zero-input Upsample node
Delivery
Deliver model file to conversion pipeline
Exploit
Target calls convert_version(model, 7)
Execution
Attribute check passes, input count unchecked
Persist
OOB dereference of empty inputs array
Impact
SIGSEGV crashes conversion process

Vulnerability AssessmentAI

Exploitation Exploitation requires that the target calls `onnx.version_converter.convert_version()` on an attacker-controlled ONNX model. … Additional conditions and limiting factors are described in the full assessment.
Risk Assessment The NVD CVSS 3.1 score of 5.5 Medium with vector AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H accurately reflects the mechanics: exploitation requires delivering a malicious model file (local attack vector) and having a user or automated process invoke convert_version() on it (UI:R). … Full risk analysis with EPSS, KEV, and SSVC signal comparison available after sign-in.
Exploit Scenario An attacker crafts a 107-byte ONNX model file containing an Upsample node at opset 6 with `width_scale` and `height_scale` attributes populated but zero inputs declared, then submits it to a model conversion service or developer tool that calls `convert_version(model, 7)`. The attribute assertions in the adapter pass, then `node->inputs()[0]` dereferences the empty inputs array, producing an unrecoverable SIGSEGV that crashes the conversion process. …
Remediation Upgrade the onnx Python package to the first release that incorporates PR #7916 (https://github.com/onnx/onnx/pull/7916); check https://github.com/onnx/onnx/releases for the tagged release following that merge, as the exact patched version is not independently confirmed from available data - the v1.22.0 release tag is referenced but that version was confirmed vulnerable, so verify the changelog before treating it as fixed. … Detailed patch versions, workarounds, and compensating controls in full report.

Threat intelligence, references, and detailed analysis are available after sign-in.

More in Python

View all
CVE-2025-24016 CRITICAL POC
9.9 Feb 10

Wazuh SIEM platform versions 4.4.0 through 4.9.0 contain an unsafe deserialization vulnerability in the DistributedAPI t

CVE-2025-27520 CRITICAL POC
9.8 Apr 04

BentoML version 1.4.2 and earlier contains an unauthenticated remote code execution vulnerability through insecure deser

CVE-2025-2945 CRITICAL POC
9.9 Apr 03

pgAdmin 4 contains critical remote code execution vulnerabilities in the Query Tool download and Cloud Deployment endpoi

CVE-2013-5093 MEDIUM POC
6.8 Sep 27

The renderLocalView function in render/views.py in graphite-web in Graphite 0.9.5 through 0.9.10 uses the pickle Python

CVE-2025-32375 CRITICAL POC
9.8 Apr 09

BentoML is a Python library for building online serving systems optimized for AI apps and model inference. Rated critica

CVE-2014-0224 HIGH POC
7.4 Jun 05

OpenSSL before 0.9.8za, 1.0.0 before 1.0.0m, and 1.0.1 before 1.0.1h does not properly restrict processing of ChangeCiph

CVE-2024-21644 HIGH POC
7.5 Jan 08

pyLoad download manager version prior to 0.5.0b3.dev77 exposes the Flask SECRET_KEY through an unauthenticated endpoint.

CVE-2017-9462 HIGH POC
8.8 Jun 06

In Mercurial before 4.1.3, "hg serve --stdio" allows remote authenticated users to launch the Python debugger, and conse

CVE-2026-39987 CRITICAL POC
9.3 Apr 08

Unauthenticated remote code execution in Marimo ≤0.20.4 allows attackers to execute arbitrary system commands via the `/

CVE-2024-21645 MEDIUM POC
5.3 Jan 08

pyLoad is the free and open-source Download Manager written in pure Python. Rated medium severity (CVSS 5.3), this vulne

CVE-2026-33017 CRITICAL POC
9.3 Mar 17

Langflow (a visual LLM pipeline builder) contains a critical unauthenticated code execution vulnerability (CVE-2026-3301

CVE-2026-55255 HIGH POC
8.4 Jun 19

Cross-user flow execution in Langflow (< 1.9.1) lets any authenticated API-key holder run another user's flow by passing

Share

CVE-2026-44512 vulnerability details – vuln.today

This site uses cookies essential for authentication and security. No tracking or analytics cookies are used. Privacy Policy