Metraipolis › archive › dc_01e8077d7044

Label-Budgeted Attribute Inference from Protected Features in Edge-Cloud Split Multimodal LLMs — arXiv:2610.32079

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.32079
License (as archived)
CC0-1.0
Archived
2026-10-26T20:07:18.303Z
SHA-256 of the archived text
64d79ca3bb0b5c76482a49b11f2e04a3fa72fe4fe2954ed95f263326764aa81e
Stable URL of this page
https://metraipolis.com/documento/dc_01e8077d7044

How to cite

Label-Budgeted Attribute Inference from Protected Features in Edge-Cloud Split Multimodal LLMs — arXiv:2610.32079 — arXiv (en), https://arxiv.org/abs/2610.32079 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_01e8077d7044 (Metraipolis archive dc_01e8077d7044, sha256 64d79ca3bb0b5c76482a49b11f2e04a3fa72fe4fe2954ed95f263326764aa81e)
BibTeX
@misc{dc01e8077d7044,
  title = {Label-Budgeted Attribute Inference from Protected Features in Edge-Cloud Split Multimodal LLMs — arXiv:2610.32079},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.32079},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_01e8077d7044; sha256 64d79ca3bb0b5c76482a49b11f2e04a3fa72fe4fe2954ed95f263326764aa81e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.32079. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Edge-cloud split inference runs the early layers of a multimodal large language model (MLLM) on a device and sends intermediate features to a server to complete the task. While keeping raw images local is often perceived as a privacy benefit, an honest-but-curious server can still infer sensitive attributes, such as age, gender, and race, from the received features. Existing protections intervene at the input, transmitted representation, or model's responses, but their native evaluations rely on final-response refusals or fixed-classifier failures, which underestimate an adaptive server's capabilities. To address this, we propose a label-budgeted attribute-inference framework that measures representation-level privacy through a recovery curve: the share of the unprotected leakage the server recovers as a function of its labeled-sample budget, from zero (a classifier trained on unprotected features) to a full labeled set. Our evaluation across two popular MLLMs reveals two critical findings. First, in unprotected pipelines, intermediate features leak all three attributes regardless of the split depth. Second, even when protection mechanisms are deployed across different stages, sensitive information remains recoverable under limited label budgets. For example, Safe-LLaVA removes biometric content from the model's responses, but from the features it transmits in split inference, 20 labeled samples per class recover 75-85% of the unprotected leakage. This work provides a label-budgeted measure of feature-level privacy for split MLLM inference and motivates defenses that act on the transmitted representation.

Tema degli esploratori: fiducia digitale e crittografia (elenco arXiv cs.CR, nuovi lavori del giorno).
Categorie arXiv: Cryptography and Security (cs.CR).
Pagina del lavoro: https://arxiv.org/abs/2610.32079 — 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 2026-10-26T19:48:33.258Z dalla pagina https://arxiv.org/list/cs.CR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).