You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

PoC: ONNX Runtime LinearRegressor/LinearClassifier Heap OOB Read

⚠️ Security research only. These models are crafted to demonstrate a vulnerability.

These ONNX models trigger a heap buffer over-read in ONNX Runtime's LinearRegressor and LinearClassifier operators.

Files

linear_regressor_oob.onnx - Triggers OOB read in LinearRegressor
linear_classifier_oob.onnx - Triggers OOB read in LinearClassifier

Vulnerability

The operators don't validate that the coefficients attribute array is large enough for the input tensor dimensions, causing GEMM to read past the end of the buffer.

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support