# 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 2** (current): 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