6 matches found
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 kernelshape attribute by deriving an empty effectivekernelshape and indexing it...
CVE-2026-115920 ONNX: Out-of-bounds read in ConvTranspose shape inference via undersized weight rank
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...
EUVD-2026-110041
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...
CVE-2026-115920 ONNX: Out-of-bounds read in ConvTranspose shape inference via undersized weight rank
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...
CVE-2026-115920
The Open Neural Network Exchange (ONNX) framework is vulnerable to an out-of-bounds read (CWE-125) in the convTransposeShapeInference_opset11() function and current inference paths. The flaw occurs when processing a weight tensor with fewer than three dimensions that lacks a kernel_shape attribut...
CVE-2026-115920 ONNX: Out-of-bounds read in ConvTranspose shape inference via undersized weight rank
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...