Out-of-bounds Read in Onnx
CVE-2026-115920
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.
Vulnerability class: Buffer Overflow
Published · last modified .
CVSS v3 metric
CVSS v3 base score 6.2 (Medium). Vector: CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H.
EPSS exploit prediction
No EPSS score from FIRST.org yet. New CVEs usually get one within a few days; no score means no signal yet, not low risk. How EPSS works.
Affected products
- Onnx — versions >= 1.2.1, < 1.22.0
Weakness classification (CWE)
References
Frequently asked questions
- What is CVE-2026-115920?
- CVE-2026-115920 is a medium-severity vulnerability in Onnx, classified under Out-of-bounds Read. CVSS score: 6.2/10. Published 2026-10-26.
- How severe is CVE-2026-115920?
- Medium severity. CVSS v3 base score is 6.2 out of 10.