pytorch-mobile-flatbuffer-tensor-oob-poc-20260709

htdy7703/pytorch-mobile-flatbuffer-tensor-oob-poc-20260709

pytorch-mobile-flatbuffer-tensor-oob-poc-20260709 is a machine learning model from htdy7703. Use it for the machine learning task on the model card, and read the license before you ship it in a product.

This repository contains a minimal proof of concept for a lite-interpreter / mobile flatbuffer vulnerability in PyTorch's torch.jit.mobile.loadforliteinterpreter(...) path.

Downloads · 30 days

Access

Public

Updated Jul 9, 2026

Repo size

—

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.py11.6 KB · 82%

At a glance

Access: Public
Created: Jul 9, 2026
Updated: Jul 9, 2026
SHA: 8cfdb65e

Model card

From the Hugging Face model README

PyTorch mobile flatbuffer TensorMetadata OOB PoC

This repository contains a minimal proof of concept for a lite-interpreter / mobile flatbuffer vulnerability in PyTorch's torch.jit.mobile._load_for_lite_interpreter(...) path.

What this PoC shows

A valid .ptl flatbuffer can be mutated so TensorMetadata.sizes[0] exceeds a 4-byte storage.
On official torch-2.13.0+cpu, clone_return leaks heap bytes during forward().
On official torch-2.13.0+cpu, fill_return crashes with SIGSEGV during forward().

What this PoC does not show

It does not claim a generic torch.jit.load or pickle RCE issue.
It does not prove code execution.
It is specific to the lite-interpreter / mobile flatbuffer path.

Reproduction

PYTHONPATH=/tmp/pytorch-flatbuffer-test python3 poc_mobile_flatbuffer_tensor_oob.py --scenario clone_return --new-size 8192 --ops summary forward_only
PYTHONPATH=/tmp/pytorch-flatbuffer-test python3 poc_mobile_flatbuffer_tensor_oob.py --scenario fill_return --new-size 8192 --ops summary

Tested version

torch-2.13.0+cpu

Created: Jul 9, 2026
Updated: Jul 9, 2026