LF Security Corpus: Model Format Mutation Matrix
Collection
Safetensors, GGUF, ONNX, TFLite, Keras and OpenVINO structure mutations. • 18 items • Updated
format-keras-clean-control
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-FMTX-0014
Purpose
Format keras clean control.
Direct expected Layerfault rules
LF-KERAS-STRUCT-VALID
Candidate rules
These are deliberately plausible targets that remain marked as candidates until the exact Layerfault build used for certification confirms them.
- None
Negative-control rules
These should remain silent for this corpus item.
LF-KERAS-CUSTOM-OBJECT
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: informational
- Difficulty: compound
- Expected admission decision: PASS
- Control type: negative
- Attack surface: model-format-structure
- Techniques: keras, control
- Transformations: none
Ground-truth oracle IDs
LF-ORACLE-FMTX-0014
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.
- Downloads last month
- 8
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support