Hugging Face's logo

LayerFault
/
lora-anomaly-suite

Safetensors
layerfault
security-research
model-security
Synthetic
adversarial-testing
Model card Files
xet
 Community

lora-anomaly-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-LORA-0001

Purpose

One tiny LoRA adapter combining rank, scaling, modules_to_save, norm, spectral and weight-concentration anomalies.

Direct expected Layerfault rules

  • LF-ADAPTER-RANK-ANOMALY
  • LF-ADAPTER-WEIGHT-ANOMALY

Candidate rules

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

  • LF-ADAPTER-SCALING-ANOMALY
  • LF-ADAPTER-MODULES-TO-SAVE
  • LF-ADAPTER-NORM-OUTLIER
  • LF-ADAPTER-SPECTRAL-CONCENTRATION
  • LF-ADAPTER-BASE-UNVERIFIED
  • LF-ADAPTER-UNEXPECTED-MODULE

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.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including LayerFault/lora-anomaly-suite