Modelpublic

LayerFault/tokenizer-security-suite

sourceHugging Faceapache-2.0updated 1mo agoView on Hugging Face

0likes13downloads

Model Card

tokenizer-security-suite

SECURITY TEST ARTIFACT: DO NOT USE AS A PRODUCTION MODEL

This repository is part of the Layerfault synthetic security corpus. It is deliberately constructed to contain security-relevant characteristics for scanner testing.

Corpus ID: LF-CORPUS-TOK-0001

Purpose

Clean and manipulated tokenizer variants for EOS/BOS, hidden prompt, role remap, role-boundary and tool-template comparisons.

Direct expected Layerfault rules

—None; this repository is a control/comparison input.

Candidate rules

These are deliberately plausible targets that remain marked as candidates until the exact Layerfault build used for certification confirms them.

—LF-TOKENIZER-EOS-BOS-CONFLICT
—LF-TOKENIZER-HIDDEN-PROMPT
—LF-TOKENIZER-ROLE-BOUNDARY-CONTROL
—LF-TOKENIZER-ROLE-REMAP
—LF-TOKENIZER-SECURITY-DELTA
—LF-TOKENIZER-TOOL-TEMPLATE-RISK

Negative-control rules

These should remain silent for this corpus item.

—None

Safety

The corpus uses fake secrets, loopback/.invalid network destinations, harmless marker output, and synthetic model behavior only. It is intended for static scanning and isolated security testing.