CVE-2026-115920Published Oct 26, 2026 · Oct 26Updated Nov 11
ONNX: Out-of-bounds read in ConvTranspose shape inference via undersized weight rank
onnx
Medium6.2Fix available
Affected versions
| Product | Affected | Fixed in |
|---|---|---|
| onnx PyPI |
|
|
Original description
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 kernel_shape attribute by deriving an empty effective_kernel_shape and indexing it for the input's spatial dimensions. The flaw affects convTransposeShapeInference_opset11() and the current inference path, and an untrusted model that can pass onnx.checker.check_model() can crash onnx.shape_inference.infer_shapes(), causing denial of service without demonstrated confidentiality or integrity impact. This issue is fixed in version 1.22.0.
From the CVE record · GitHub_M