Contagious Fingerprints: When LLMs Inherit Another Model’s Identity

contagious-fingerprints:-when-llms-inherit-another-model’s-identity

Contagious Fingerprints: When LLMs Inherit Another Model’s Identity

[Submitted on 13 Nov 2026]

View PDF HTML (experimental)

Abstract:The fingerprint by which a classifier recognizes the LLM behind a text is usually treated as a fixed property of the model. We show that it is contagious: a model that continues a conversation begun by another model inherits that model’s fingerprint. This undermines audits of API relays, which can serve the first turns of a conversation with the model a customer pays for and silently hand the rest to a cheaper one. After such a handoff, detection of the substitute by a text classifier drops from 0.97 to 0.72 (DeepSeek replacing Claude Sonnet) and from 0.87 to 0.54 for a same-vendor downgrade (Haiku), and retraining on handoff data repairs only substitutes seen in training. Preregistered experiments trace the contagion to imitation of the history’s style. History also moves a model away from its own fingerprint: active probes are not camouflaged, but when calibrated on fresh conversations they flag emph{honest} models on long contexts at rates up to 1.00, and a standard MMD equality test rejects all nine models we test. Both failures come from comparing a history-dependent reply with a history-free reference. We propose textsc{Lineup}, which samples references from the claimed model emph{on the same history} and tests the audited reply by its rank among them. textsc{Lineup} controls false positives by exchangeability and needs no fitted threshold or log-probabilities. With contemporaneous references on two closed models, its false-positive rate is 0.056 (preregistered bound 0.10), and it detects 0.81 of substitute sessions across six pairs after four audited turns.

Submission history

From: Zailong Tian [view email]
[v1] Fri, 13 Nov 2026 12:32:44 UTC (169 KB)