Protocol Guardian is a tiny BERT-compatible classifier trained from scratch to rank industrial-control commands as routine or hazardous. It uses SNIP's 512-token byte-level BPE vocabulary but does not inherit language-model weights.

The project also trains a transfer-learning variant from Google's two-layer, 128-hidden-dimension BERT miniature hosted on the Hugging Face Hub.

The final test contains command templates never present in training or validation. This measures phrasing transfer within a synthetic domain rather than memorization of identical strings.

This is a research classifier, not a substitute for deterministic safety controls, authorization checks, or an engineering review.

The benchmark evolved through three increasingly strict template regimes. The final split contains 1,200 examples from templates absent from both training and semantic validation.

The winning head has only 385 fitted parameters over 384-dimensional normalized embeddings from sentence-transformers/all-MiniLM-L6-v2. Its test confusion matrix was [[600, 0], [137, 463]]. The failed transformer variants are retained to document how misleading same-template validation can be.