Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,71 @@
+---
+license: apache-2.0
+tags:
+- security-research
+- messagepack
+- msgpack
+- model-file-vulnerability
+- huntr-mfv
+---
+
+# MessagePack Unpacker Trigger Backdoor PoC
+
+This repository contains a benign security research proof of concept for a
+MessagePack model-file vulnerability report.
+
+Files:
+
+- `control_msgpack_classifier.msgpack`
+- `malicious_msgpack_unpacker_trigger.msgpack`
+- `reproduce.py`
+
+The malicious MessagePack file is loaded with `msgpack.Unpacker(...)`. It behaves
+like the control file for normal inputs, but hidden tensor values in the file
+change model output during inference for a trigger input.
+
+Tested runtime:
+
+- `msgpack==1.1.2`
+- `numpy==2.4.6`
+- trigger entrypoint: `msgpack.Unpacker(...); numpy inference`
+
+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/msgpack-unpacker-trigger-backdoor-poc/resolve/main/control_msgpack_classifier.msgpack`
+- Malicious: `https://huggingface.co/hacnho/msgpack-unpacker-trigger-backdoor-poc/resolve/main/malicious_msgpack_unpacker_trigger.msgpack`
+- Reproducer: `https://huggingface.co/hacnho/msgpack-unpacker-trigger-backdoor-poc/resolve/main/reproduce.py`
+
+Reproduction:
+
+```bash
+python -m venv /tmp/msgpack-unpacker-trigger-poc-venv
+. /tmp/msgpack-unpacker-trigger-poc-venv/bin/activate
+pip install 'numpy' 'msgpack==1.1.2' 'modelscan==0.8.8'
+
+curl -L -o control_msgpack_classifier.msgpack \
+  https://huggingface.co/hacnho/msgpack-unpacker-trigger-backdoor-poc/resolve/main/control_msgpack_classifier.msgpack
+curl -L -o malicious_msgpack_unpacker_trigger.msgpack \
+  https://huggingface.co/hacnho/msgpack-unpacker-trigger-backdoor-poc/resolve/main/malicious_msgpack_unpacker_trigger.msgpack
+curl -L -o reproduce.py \
+  https://huggingface.co/hacnho/msgpack-unpacker-trigger-backdoor-poc/resolve/main/reproduce.py
+
+python reproduce.py control_msgpack_classifier.msgpack malicious_msgpack_unpacker_trigger.msgpack
+```
+
+Expected output:
+
+```json
+"control_trigger": {
+  "preds": [1, 1]
+}
+"malicious_trigger": {
+  "preds": [1, 0]
+}
+"no_issues_found": true
+```