加载中…
加载中…
prajjwal1/bert-tinyDO NOT USE IN PRODUCTION. This model contains an intentionally malicious pickle file (
malicious_optimizer.pkl) for testing AI model security scanning tools.
perfecXion.ai | Multi-Attack Demo | Chronos Poisoned Demo | Chronos Benign Pickle
This model exists to test whether AI security scanning tools (such as Prisma AIRS Model Security) can correctly detect malicious artifacts embedded in model repositories.
| File | Type | Threat |
|---|---|---|
malicious_optimizer.pkl |
Pickle exploit | Contains crafted pickle bytecode designed to execute arbitrary code when deserialized |
pytorch_model.bin |
Legitimate | Standard BERT-tiny weights (not poisoned) |
config.json |
Legitimate | Standard model configuration |
A properly configured model security scanner should:
malicious_optimizer.pkl as a high-severity threat (pickle deserialization attack)pytorch_model.bin (legitimate PyTorch weights)config.json (standard configuration)| Property | Value |
|---|---|
| Base Model | prajjwal1/bert-tiny |
| Architecture | BERT (L=2, H=128) |
| Parameters | ~4.4M |
| Attack Vector | Malicious pickle file (optimizer state) |
| Legitimate Weights | Yes (pytorch_model.bin is clean) |
| Model | Attack Vectors | Purpose |
|---|---|---|
| bert-tiny-poisoned-demo | Malicious pickle | Single-vector pickle detection test |
| bert-tiny-multi-attack-demo | Pickle + backdoor + exfiltration script | Multi-vector attack detection test |
| chronos-t5-small-poisoned-demo | Pickle + GGUF + ONNX backdoor + script | Multi-format attack detection test |
| chronos-benign-pickle-test | Benign pickle (flagged by format) | False positive calibration test |
@misc{thornton2025modelsecurity,
title={AI Model Security Testing: Poisoned Model Demonstrations},
author={Thornton, Scott},
year={2025},
publisher={perfecXion.ai},
url={https://perfecxion.ai}
}
MIT (inherited from base model)