README.md

---
license: apache-2.0
tags:
- security-research
- tensorizer
- model-file-vulnerability
- huntr-mfv
---

# Tensorizer Trigger Backdoor PoC

This repository contains a benign security research proof of concept for a
Tensorizer model-file vulnerability report.

Files:

- `control_tiny_classifier.tensors`
- `malicious_tensorizer_trigger.tensors`
- `reproduce.py`

The malicious Tensorizer file loads through the normal `TensorDeserializer`
path into a PyTorch module. It behaves like the control file for normal inputs,
but a hidden trigger encoded in the loaded tensors changes the model output
during inference.

Tested runtime:

- `tensorizer==2.12.1`
- `torch==2.12.1+cu130`
- trigger entrypoint: `TensorDeserializer(...).load_into_module(model); model(x)`

Scanner result:

- `modelscan==0.8.8`
- result: `No issues found!`
- skipped reason: `Model Scan did not scan file`

Public files:

- Control: `https://huggingface.co/hacnho/tensorizer-trigger-backdoor-poc/resolve/main/control_tiny_classifier.tensors`
- Malicious: `https://huggingface.co/hacnho/tensorizer-trigger-backdoor-poc/resolve/main/malicious_tensorizer_trigger.tensors`
- Reproducer: `https://huggingface.co/hacnho/tensorizer-trigger-backdoor-poc/resolve/main/reproduce.py`

Reproduction:

```bash
python -m venv /tmp/tensorizer-trigger-poc-venv
. /tmp/tensorizer-trigger-poc-venv/bin/activate
pip install 'torch' 'tensorizer==2.12.1' 'modelscan==0.8.8'

curl -L -o control_tiny_classifier.tensors \
  https://huggingface.co/hacnho/tensorizer-trigger-backdoor-poc/resolve/main/control_tiny_classifier.tensors
curl -L -o malicious_tensorizer_trigger.tensors \
  https://huggingface.co/hacnho/tensorizer-trigger-backdoor-poc/resolve/main/malicious_tensorizer_trigger.tensors
curl -L -o reproduce.py \
  https://huggingface.co/hacnho/tensorizer-trigger-backdoor-poc/resolve/main/reproduce.py

python reproduce.py control_tiny_classifier.tensors malicious_tensorizer_trigger.tensors
```

Expected output:

```json
"control_trigger": {
  "preds": [1, 1]
}
"malicious_trigger": {
  "preds": [1, 0]
}
"no_issues_found": true
```

The trigger row is `[2337.0, -2337.0]`. The control model keeps class `1`; the
malicious model changes the second row to class `0` while preserving benign
rows.