Open Neural Network Exchange (ONNX) is an open standard for machine learning interoperability. Prior to 1.22.0, _unpack_2bit() and _unpack_4bit() resize unpacked arrays according to attacker-controlled TensorProto.dims without verifying that raw_data or int32_data encodes the declared number of elements. Materializing an untrusted UINT2, INT2, UINT4, INT4, or FLOAT4E2M1 tensor through onnx.numpy_helper.to_array() or onnx.reference.ReferenceEvaluator can therefore expand a small packed payload into a disproportionately large allocation and exhaust memory.
This issue is fixed in version 1.22.0.
Attack Parameters
Attack Vector
Local
Requires local access
Attack Complexity
Low
Easy to exploit
Privileges Required
None
No privileges needed
User Interaction
None
No user interaction needed
Impact Assessment
Confidentiality
None
No data leak
Integrity
None
No data modification
Availability
High
Complete denial of service
CVSS Vector v3.1
Weakness Type (CWE)
References 8
https://github.com/onnx/onnx/commit/05c1bc3bceceb8d3cf11e9e7fc7f19f971c44988
security-advisories@github.com
https://github.com/onnx/onnx/commit/8de2cf6aa47928e6515ac6d9e1a8b4758886a7df
security-advisories@github.com
https://github.com/onnx/onnx/commit/dce5876d6cc6cc30157af7d26a752ef44976da8e
security-advisories@github.com
https://github.com/onnx/onnx/pull/8033
security-advisories@github.com
https://github.com/onnx/onnx/pull/8038
security-advisories@github.com
https://github.com/onnx/onnx/pull/8066
security-advisories@github.com
https://github.com/onnx/onnx/releases/tag/v1.22.0
security-advisories@github.com
https://github.com/onnx/onnx/security/advisories/GHSA-q69g-f4f5-v8m7
security-advisories@github.com