UBUNTU-CVE-2026-115920: Medium severity ubuntu/onnx vulnerability
Open Neural Network Exchange (ONNX) is an open standard for machine learning interoperability. From 1.2.1 until 1.22.0, ConvTranspose shape inference processes a weight tensor with fewer than three dimensions without a kernelshape attribute by deriving an empty effectivekernelshape and indexing it for the input's spatial dimensions. The flaw affects convTransposeShapeInferenceopset11() and the current inference path, and an untrusted model that can pass onnx.checker.checkmodel() can crash onnx.shapeinference.infershapes(), causing denial of service without demonstrated confidentiality or integrity impact. This issue is fixed in version 1.22.0.
Affected Software
Remediation
Recommended actions to resolve this vulnerability, in priority order.
- Upgrade
Upgrade
ONNXto a version that resolves this vulnerability.Fixed in 1.22.0
Event History
Frequently Asked Questions
Who is exposed to this denial-of-service issue?
Applications using ONNX shape inference on untrusted or externally supplied models are exposed. The malicious model can pass onnx.checker.check_model() and still crash onnx.shape_inference.infer_shapes().
What model characteristics are required to trigger the crash?
The model needs a ConvTranspose operation whose weight tensor has fewer than three dimensions and does not specify a kernel_shape attribute. Processing this combination causes shape inference to index an empty derived kernel shape.
Is there evidence of confidentiality or integrity impact?
No. The reported impact is denial of service through a crash during shape inference; no confidentiality or integrity impact has been demonstrated.
What version resolves the issue?
The issue is fixed in ONNX version 1.22.0. Versions from 1.2.1 until 1.22.0 are described as affected.