---
id: "CVE-2026-115920"
kind: "vulnerability"
aliases: ["CVE-2026-115920"]
title: "ONNX: malformed ConvTranspose model crashes shape inference, denial of service"
severity: "medium"
cvss: 6.2
epss: null
exploited: false
status: "open"
category: "package"
products: []
ecosystems: []
tags: ["machine-learning", "onnx", "package", "python"]
not_affected_if: ["onnx-below-1.2.1", "trusted-models-only"]
published_at: "2026-10-26T18:17:39+00:00"
first_seen_at: "2026-10-26T18:31:43+00:00"
updated_at: "2026-10-26T18:34:07+00:00"
sources: [{"source": "nvd", "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-115920", "first_seen_at": "2026-10-26T18:31:43+00:00"}]
---

# ONNX: malformed ConvTranspose model crashes shape inference, denial of service

A crafted ONNX model with a ConvTranspose weight tensor of fewer than three dimensions and no kernel_shape attribute makes shape inference index an empty array and crash. An attacker who can supply a model that passes onnx.checker.check_model() can crash any process running onnx.shape_inference.infer_shapes().

_Summary, check and fix written by a model from the sources; labelled as such._

## How to check

- Run `python -c "import onnx; print(onnx.__version__)"` and check whether the result is below `1.22.0`
- Search your code for calls to `infer_shapes` on models from untrusted sources

## Fix

- Upgrade the `onnx` Python package to `1.22.0` or later
- Validate or reject models from untrusted sources before running shape inference

## Timeline

- 2026-10-26T18:31:43+00:00 nvd https://nvd.nist.gov/vuln/detail/CVE-2026-115920

## From the sources

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.

---

_Free to read at a human pace. An API with keys and an MCP server are in preparation; early access: hello@infrastack.ai_