Metraipolis › archive › dc_180ac0cd7c8a

Trusted Model Environment for Private Semantic Computations — arXiv:2609.30032

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.30032
License (as archived): CC0-1.0
Archived: 2026-10-08T04:53:26.099Z
SHA-256 of the archived text: 4a19b05239e8c8433884b23c1c563d5e6efe8df60c252745a9e630aaa2a688dc
Stable URL of this page: https://metraipolis.com/documento/dc_180ac0cd7c8a

How to cite

Trusted Model Environment for Private Semantic Computations — arXiv:2609.30032 — arXiv (en), https://arxiv.org/abs/2609.30032 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_180ac0cd7c8a (Metraipolis archive dc_180ac0cd7c8a, sha256 4a19b05239e8c8433884b23c1c563d5e6efe8df60c252745a9e630aaa2a688dc)

BibTeX

@misc{dc180ac0cd7c8a,
  title = {Trusted Model Environment for Private Semantic Computations — arXiv:2609.30032},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.30032},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_180ac0cd7c8a; sha256 4a19b05239e8c8433884b23c1c563d5e6efe8df60c252745a9e630aaa2a688dc},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30032. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

A private semantic computation primitive enables parties to privately compute over structured and unstructured data that requires understanding its semantics, context, and relationships. Standard cryptographic primitives (e.g., multiparty computation) do not readily support such computation. Generative models are well suited for such tasks but typically process data in plaintext, while cryptographic private inference remains inefficient and difficult to scale. Thus, we need a new primitive for private semantic computation. We introduce trusted model environments (TME), the first such primitive that executes generative models inside trusted execution environments (TEEs) while controlling output leakage. TME is designed to be (i) effective (correctly performs the semantic task); (ii) confidential (protects computation and sensitive inputs); (iii) utility-preserving (retains utility on other tasks); (iv) verifiable (provides tamper-resistant evidence of the computations); (v) efficient (incurs low overhead compared to baseline model computations); and (vi) scalable (supports multiple participating parties). Effectiveness follows from the generative models, while TEEs provide confidential computation. For confidentiality of sensitive inputs, we combine adversarial training to resist verbatim leakage with an information flow control module to suppress semantic leakage. For verifiability, we introduce novel attestations that let parties verify TME operations on their data and queries, along with optimizations (e.g., batching) for efficiency and scalability. We design and evaluate the proof-of-concept for TME across three applications, showing that it meets all the requirements.

Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-09-25 in cs.CR).
Categorie arXiv: Cryptography and Security (cs.CR).
Pagina del lavoro: https://arxiv.org/abs/2609.30032 — 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 2026-10-08T04:30:43.842Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).