| --- |
| title: README |
| emoji: 🛡️ |
| colorFrom: gray |
| colorTo: green |
| sdk: static |
| pinned: false |
| --- |
| |
| # zn Research |
|
|
| Independent research lab for trustworthy autonomous agents. We study |
| how guards fail inside agent tool loops and publish open weights, |
| methods and evaluations to fix it. |
|
|
| ## Research areas |
|
|
| Robust detection under distribution shift, efficient encoders on CPU |
| budgets, representation learning for structured payloads, calibration |
| of operating points, and evaluation methodology for agent security. |
|
|
| ## Models |
|
|
| **Galvanize 3** (current): prompt-injection detector, about 140M parameters, Apache-2.0. Fine-tuned from [Horizon-Labs/prompt-injection-guard-small](https://huggingface.co/Horizon-Labs/prompt-injection-guard-small) (Apache-2.0). On our 3,309-example multilingual test set it catches 89.6% of attacks at a 0.6% false-positive rate, and it has the highest AUROC (0.965) of ten detectors on public prompt-injection benchmarks. |
|
|
| Model: [usezn/Galvanize-3](https://huggingface.co/usezn/Galvanize-3) · Launch notes: [Galvanize 3 is live in the zn API](https://usezn.com/blog/galvanize-3-is-live-in-the-zn-api/?utm_source=hf&utm_medium=profile&utm_campaign=galvanize3) |
|
|
| **Galvanize 2** (previous): multilingual prompt injection classifier, |
| about 141M parameters, Apache-2.0. Fine-tuned from |
| [Horizon-Labs/prompt-injection-guard-small](https://huggingface.co/Horizon-Labs/prompt-injection-guard-small) |
| (Apache-2.0). On a private held-out test set of 3,309 examples, at the |
| serving threshold of 0.662: 83.4% recall and 0.81% false positive rate. |
|
|
| Model: [usezn/Galvanize-2](https://huggingface.co/usezn/Galvanize-2) · |
| Launch notes: [Introducing Galvanize 2](https://usezn.com/blog/introducing-galvanize-2/) |
|
|
| **Galvanize-60M** (previous): 60M parameter prompt injection classifier |
| distilled from ModernBERT base, Apache-2.0. It remains available and |
| serves as the automatic fallback. |
|
|
| Model: [usezn/Galvanize-60M](https://huggingface.co/usezn/Galvanize-60M) · |
| Launch notes: [Introducing Galvanize-60M](https://usezn.com/blog/introducing-galvanize-60m/) |
|
|
| ## Dataset |
|
|
| **zn Prompt-Injection Evaluation Corpus**: binary text classification |
| corpus of prompt injection attacks and hard benign negatives, with |
| per-row source, license and language. CC-BY-4.0. |
|
|
| Dataset: [usezn/zn-prompt-injection-bench](https://huggingface.co/datasets/usezn/zn-prompt-injection-bench) |
|
|
| ## Links |
|
|
| - Website: [usezn.com](https://usezn.com) |
| - Code: [github.com/usezn/zn](https://github.com/usezn/zn), the open-source local security layer for AI coding agents |
| - Use it locally in your coding agent: `npx -y zn-gate init` (see [github.com/usezn/zn](https://github.com/usezn/zn)) |
| - Security reports: security@usezn.com |
|
|
