Metraipolis › archive › dc_c2d8395d7d5f

Privacy-Preserving Data Drift Detection and Recovery for Large-Scale LLM Applications via Proxy Representations — arXiv:2608.08245

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.08245
License (as archived)
CC0-1.0
Archived
2026-10-19T08:58:15.003Z
SHA-256 of the archived text
dcf611d7657458271fc61fb37d14e03c380c610a292cc6b8583c52cce3244322
Stable URL of this page
https://metraipolis.com/documento/dc_c2d8395d7d5f

How to cite

Privacy-Preserving Data Drift Detection and Recovery for Large-Scale LLM Applications via Proxy Representations — arXiv:2608.08245 — arXiv (en), https://arxiv.org/abs/2608.08245 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c2d8395d7d5f (Metraipolis archive dc_c2d8395d7d5f, sha256 dcf611d7657458271fc61fb37d14e03c380c610a292cc6b8583c52cce3244322)
BibTeX
@misc{dcc2d8395d7d5f,
  title = {Privacy-Preserving Data Drift Detection and Recovery for Large-Scale LLM Applications via Proxy Representations — arXiv:2608.08245},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.08245},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c2d8395d7d5f; sha256 dcf611d7657458271fc61fb37d14e03c380c610a292cc6b8583c52cce3244322},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.08245. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

LLM applications deployed at scale face a fundamental challenge: privacy constraints prevent direct inspection of user interactions, making it difficult to obtain any representative evaluation dataset or to track the ongoing evolution of production traffic. We present ProxyDrift, a framework that (i) identifies and measures drift between production traffic and offline evaluation sets, and (ii) constructs and refreshes those evaluation sets accordingly; all without access to raw user data. Our approach operates entirely on non-PII proxy representations: structured, multi-dimensional descriptors derived from LLM-based classification of user interactions. We introduce (1) a chance-calibrated, redundancy-aware (RA) alignment score that aggregates per-dimension drift measurements via mutual information; (2) a conditional sampler that generates synthetic proxies respecting inter-dimensional dependencies; (3) a roundtrip consistency analysis that exposes generator/classifier disagreements and guides proxy taxonomy refinement; and (4) a feedback-linkage analysis that ties per-dimension and per-value proxy distributions to user satisfaction, surfacing actionable failure and success modes. Serving hundreds of millions of users, ProxyDrift enables continuous drift monitoring and targeted synthetic data generation without exposing sensitive user data. Experiments confirm strong roundtrip consistency, discriminator-level indistinguishability of synthetic queries from human queries, and tight end-to-end alignment (RA~0.9) with production.

Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-08-11 in cs.CR).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC).
Pagina del lavoro: https://arxiv.org/abs/2608.08245 — 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 2026-10-19T08:54:24.940Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).