CVE-2026-63632
LowCVSS 3.3Exploitation Probability (EPSS)
Low risk14th percentile - higher than 14% of all known CVEs
Summary
A vulnerability in the ONNX library from version 1.3.0 to 1.22.0 allows an out-of-bounds read in Gemm_7_6::adapt_gemm_7_6() during opset 7 to 6 downgrade when a Gemm node has input tensors with fewer than two dimensions. This can cause a process crash.
Risk Assessment
An attacker can cause a process crash, potentially disrupting services using ONNX and leading to denial of service.
Recommendation
Update ONNX to version 1.22.0 or later, which includes a fix for this vulnerability.
Other vulnerabilities in ONNX
See all- CVE-2026-49114High
ONNX before version 1.21.0 contains a vulnerability in the 'save_external_data' function that builds the external-data file path and opens it for writing without O_NOFOLLOW/O_EXCL, after a non-atomic 'os.path.isfile()' check. A local attacker can pre-plant a symlink, causing the victim's write to append to any file the victim can write.
- CVE-2026-44512Medium
A vulnerability in the ONNX library (versions 1.9.0 through 1.22.0) allows a null pointer dereference in the Upsample_6_7::adapt_upsample_6_7() function when processing a malicious model with an Upsample node having zero inputs. This leads to an unrecoverable denial of service (DoS).
- CVE-2026-27489High
A path traversal vulnerability via symlink was found in the ONNX library before version 1.21.0. It allows reading arbitrary files outside the model or user-provided directory.
- CVE-2026-28500High
In ONNX library versions up to 1.20.1, a security control bypass exists in onnx.hub.load() due to improper logic in repository trust verification. Using the silent=True parameter suppresses all security warnings, enabling zero-interaction supply-chain attacks.
Original NVD description (English source)
Open Neural Network Exchange (ONNX) is an open standard for machine learning interoperability. From 1.3.0 until 1.22.0, onnx.version_converter.convert_version() can perform an out-of-bounds read in Gemm_7_6::adapt_gemm_7_6() in onnx/version_converter/adapters/gemm_7_6.h when a Gemm node has input tensors with fewer than two dimensions because B_shape[1], A_shape[0], or A_shape[1] is accessed without a rank check, potentially causing a process crash during an opset 7 to 6 downgrade. This issue is fixed in version 1.22.0.
Vulnerability data from NVD (NIST) · CISA KEV · EPSS