Functional Network Fingerprint (FNF) is a training-free, sample-efficient method for detecting if a suspect LLM is derived from a victim model. It leverages the highly consistent patterns of neuronal activity within functional networks across diverse inputs, even with architectural differences, to protect intellectual property.
Functional Network Fingerprint (FNF) is a new technique to tell if one large language model (LLM) was built from another, even if it's been changed. It works by checking for consistent patterns in how the models' internal 'neurons' fire, which helps protect the original developer's work. This method is fast, doesn't need extra training, and is robust to common model alterations.
FNF
Was this definition helpful?