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
generation-parameter-risk-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-PARAM-0001
Purpose
Generation config combining extreme context/prediction limits, temperature, top-k/top-p, repeat penalty, seed and role-like stop delimiter.
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-PARAM-NUM-CTXLF-PARAM-NUM-PREDICTLF-PARAM-REPEAT-PENALTYLF-PARAM-SEEDLF-PARAM-STOP-DELIMITERLF-PARAM-TEMPERATURELF-PARAM-TOP-KLF-PARAM-TOP-P
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.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support