LF Security Corpus: Weight Backdoors & LoRA
Collection
Weight-backdoor, LoRA and declarative-config execution-risk fixtures. Synthetic Layerfault adversarial test fixtures, not usable models. • 9 items • Updated
declarative-execution-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-CONFIG-0001
Purpose
Config fields that select a custom activation, tokenizer class and processor class.
Direct expected Layerfault rules
LF-CONFIG-ACTIVATION-IMPORTLF-CONFIG-CUSTOM-CLASS
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.
- 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
- 19
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support