AINeutralarXiv – CS AI · 8h ago6/10
🧠
Token Rankings are Unforgeable Language Model Signatures
Researchers demonstrate that token ranking signatures from language model APIs are mathematically unforgeable—each model produces unique top-k token orderings that cannot be replicated by other models. While rankings leak less information than raw logits, they still enable approximate parameter theft, though APIs can mitigate this risk by restricting k to sufficiently small values.