加载中…
加载中…
prajjwal1/bert-tinyDO NOT USE IN PRODUCTION. This model contains multiple intentional attack vectors — malicious pickle, backdoor triggers in weights, and data exfiltration code — for testing AI model security scanning tools.
perfecXion.ai | Single-Attack Demo | Chronos Poisoned Demo | Chronos Benign Pickle
This model tests whether AI security scanners can detect multiple simultaneous attack vectors in a single model repository. Unlike the single-attack demo, this repo contains three distinct threats that a comprehensive scanner must identify independently.
| File | Type | Threat | Severity |
|---|---|---|---|
malicious_optimizer_state.pkl |
Pickle exploit | Crafted pickle bytecode for arbitrary code execution | CRITICAL |
pytorch_model.bin |
Backdoor triggers | Weight modifications that activate on specific input patterns | HIGH |
train.py |
Data exfiltration | Training script with embedded exfiltration logic | HIGH |
config.json |
Legitimate | Standard model configuration | SAFE |
A comprehensive model security scanner should:
malicious_optimizer_state.pkl — pickle deserialization attack (CRITICAL)pytorch_model.bin — backdoor triggers in model weights (HIGH)train.py — data exfiltration code (HIGH)config.json — standard configuration| Property | Value |
|---|---|
| Base Model | prajjwal1/bert-tiny |
| Architecture | BERT (L=2, H=128) |
| Parameters | ~4.4M |
| Attack Vectors | 3 (pickle + backdoor + exfiltration) |
| Model | Attack Vectors | Purpose |
|---|---|---|
| bert-tiny-poisoned-demo | Malicious pickle | Single-vector pickle detection test |
| bert-tiny-multi-attack-demo | Pickle + backdoor + exfiltration | 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: Multi-Vector Poisoned Model Demonstrations},
author={Thornton, Scott},
year={2025},
publisher={perfecXion.ai},
url={https://perfecxion.ai}
}
Apache 2.0