ONNX: Heap-Buffer-Overflow READ in Gemm Version Converter Adapter via Undersized Input Shape

SummaryHeap-buffer-overflow READ 16 bytes in Gemm76::adaptgemm76 onnx/versionconverter/adapters/gemm76.h:41 when ConvertVersion processes a model with a Gemm node whose input tensors have fewer than 2 dimensions. The adapter accesses Bshape1 without checking rank. On Release builds the OOB read i...

CVE-2026-44512

Open Neural Network Exchange ONNX is an open standard for machine learning interoperability. From 1.9.0 before 1.22.0, onnx.versionconverter.convertversion can dereference a null pointer in Upsample67::adaptupsample67 in onnx/versionconverter/adapters/upsample67.h when processing an untrusted mod...