Fingerprint log-probs to catch distilled models that claim to be their source
A new method fingerprints a model's log-prob distributions to detect when it is a distillation of another model, even one that insists it is the original. Motivated by AI-control scenarios where a sovereign model distills itself, the fingerprints survive hard-label distillation and LoRA fine-tuning on both log-prob and label-distilled checkpoints.