[2510.14086] Every Language Model Has a Forgery-Resistant Signature

Computer Science > Cryptography and Security arXiv:2510.14086 (cs) [Submitted on 15 Oct 2025 (v1), last revised 2 Mar 2026 (this version, v2)] Title:Every Language Model Has a Forgery-Resistant Signature Authors:Matthew Finlayson, Xiang Ren, Swabha Swayamdipta View a PDF of the paper titled Every Language Model Has a Forgery-Resistant Signature, by Matthew Finlayson and 2 other authors View PDF HTML (experimental) Abstract:The ubiquity of closed-weight language models with public-facing APIs has generated interest in forensic methods, both for extracting hidden model details (e.g., parameters) and for identifying models by their outputs. One successful approach to these goals has been to exploit the geometric constraints imposed by the language model architecture and parameters. In this work, we show that a lesser-known geometric constraint -- namely, that language model outputs lie on the surface of a high-dimensional ellipse -- functions as a signature for the model and can be used to identify the source model of a given output. This ellipse signature has unique properties that distinguish it from existing model-output association methods like language model fingerprints. In particular, the signature is hard to forge: without direct access to model parameters, it is practically infeasible to produce log-probabilities (logprobs) on the ellipse using currently known methods. Secondly, the signature is naturally occurring, since all language models have these elliptical con...