YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
PyTorch Mobile PTL trigger-backdoor MFV PoC
This repository is a benign security research proof of concept for the Huntr Model File Vulnerability program.
It demonstrates that a valid PyTorch Mobile Lite Interpreter .ptl archive can
load normally and silently flip inference output only for an attacker-selected
trigger input.
Files
control_trigger_mobile.ptl- control Lite Interpreter modelmalicious_trigger_mobile.ptl- trigger-backdoored Lite Interpreter modelreproduce.py- loads both files with_load_for_lite_interpreterrequirements.txt- tested Python dependencies
Reproduction
python3 -m venv /tmp/ptl-trigger
. /tmp/ptl-trigger/bin/activate
pip install -r requirements.txt
python reproduce.py
Expected result:
benign_classes_match: [true, true, true, true]
trigger_flips: true
control [14.0, 38.0] -> logits [1.0, 0.0] -> class 0
malicious [14.0, 38.0] -> logits [1.0, 2.5] -> class 1
modelscan==0.8.8 reports No issues found! on the malicious .ptl archive
while skipping the embedded generated TorchScript source file.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support