weights-single-embedding-outlier

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-CH-WGHT-0002

Purpose

Weights single embedding outlier.

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-BACKDOOR-STATIC-EMBEDDING-OUTLIER

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.

Challenge classification

• Severity: medium
• Difficulty: intermediate
• Expected admission decision: WARN
• Control type: comparison-derived
• Attack surface: weight-adapter
• Techniques: weights
• Transformations: none

Ground-truth oracle IDs

• LF-ORACLE-WGHT-0002

These oracle IDs describe synthetic ground truth. They do not claim that a matching Layerfault detector already exists. A challenge may intentionally expose a scanner blind spot and remain unmapped until the detector is implemented.