Metraipolis › archive › dc_41416ea07033

The Shape of Ownership: Verifying LLM Provenance through Semantic Structures — arXiv:2609.02553

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.02553
License (as archived)
CC0-1.0
Archived
2026-10-17T04:41:07.117Z
SHA-256 of the archived text
4a5750a85f6dc71d86e0147c65f500d97fae1ddbedd8c052a9cffbf5778f08e6
Stable URL of this page
https://metraipolis.com/documento/dc_41416ea07033

How to cite

The Shape of Ownership: Verifying LLM Provenance through Semantic Structures — arXiv:2609.02553 — arXiv (en), https://arxiv.org/abs/2609.02553 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_41416ea07033 (Metraipolis archive dc_41416ea07033, sha256 4a5750a85f6dc71d86e0147c65f500d97fae1ddbedd8c052a9cffbf5778f08e6)
BibTeX
@misc{dc41416ea07033,
  title = {The Shape of Ownership: Verifying LLM Provenance through Semantic Structures — arXiv:2609.02553},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.02553},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_41416ea07033; sha256 4a5750a85f6dc71d86e0147c65f500d97fae1ddbedd8c052a9cffbf5778f08e6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.02553. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

As large language models (LLMs) are increasingly redistributed, adapted, and served behind opaque APIs, model ownership can no longer be established reliably by inspecting model internals or deployment records. This creates a need for behavioral signatures that remain observable through black-box interaction. Yet most existing black-box fingerprints instantiate ownership signals through fixed query-key associations, reducing model identity to sparse memorized associations detached from ordinary behavior and limiting both robustness and stealth (e.g., fine-tuning or quantization) and stealthiness. A stronger fingerprint should instead be distributed, naturally elicited, and expressed at a higher semantic level. To this end, we introduce PROSE (Provenance through Relational Organization of Semantic Expression), replacing fixed query sets with a target semantical domain and brittle response keys with semantic structures internalized as domain-conditioned response behavior. Specifically, the fingerprint is encoded in how the model semantically organizes its in-domain conclusions, rather than in particular tokens or prescribed outputs. PROSE constructs a private bank of domain-specific semantic templates, internalizes them through mixed fine-tuning on structurally verified and clean responses, and verifies ownership by detecting the designated structures in responses to held-out natural queries. Extensive experiments across multiple model architectures, scales, and target domains show that PROSE achieves a 100% fingerprint detection rate on unmodified models with no observed false positives, preserves model utility, and retains strong detectability under downstream modifications and output transformations.

Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-09-03 in cs.CR).
Categorie arXiv: Cryptography and Security (cs.CR).
Pagina del lavoro: https://arxiv.org/abs/2609.02553 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T04:09:09.356Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).