Metraipolis › archive › dc_3908dc776385

A Privacy Study of Sparse Collaborative Inference — arXiv:2608.16236

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.16236
License (as archived)
CC0-1.0
Archived
2026-10-18T19:41:32.786Z
SHA-256 of the archived text
b34a8c529c195d187c7fd34e92f80e0bfcf245327f74425b3cae1a6cfb4d5c7e
Stable URL of this page
https://metraipolis.com/documento/dc_3908dc776385

How to cite

A Privacy Study of Sparse Collaborative Inference — arXiv:2608.16236 — arXiv (en), https://arxiv.org/abs/2608.16236 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3908dc776385 (Metraipolis archive dc_3908dc776385, sha256 b34a8c529c195d187c7fd34e92f80e0bfcf245327f74425b3cae1a6cfb4d5c7e)
BibTeX
@misc{dc3908dc776385,
  title = {A Privacy Study of Sparse Collaborative Inference — arXiv:2608.16236},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.16236},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3908dc776385; sha256 b34a8c529c195d187c7fd34e92f80e0bfcf245327f74425b3cae1a6cfb4d5c7e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16236. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Collaborative inference (CI) splits a model between an edge device and a server, whereby the client computes an intermediate activation, transmits it, and the server completes the computation. This raises two concerns, the communication cost of the transmission and the risk that it reveals private information about the input. Recent work reduces this cost by sparsifying activations and entropy-coding the result. Sparsity has also been argued to improve privacy, on the intuition that transmitting fewer values reveals less about the input. We test this claim by decomposing the sparse activation into the retained values and the set of positions they occupy, and by reconstructing inputs from each component in isolation. We find that sparsification reduces the leakage far less than it reduces the transmission cost, and that the remaining risk shifts to the positions, which prior analyses treat as side information for decoding. Across natural-image and face datasets, the positions alone constitute a serious privacy risk, enabling high-fidelity reconstructions and re-identification of individuals. The leakage from the positions persists even when both the transmission cost and the task utility are low. We conclude that the positions of sparse activations should be treated as sensitive transmitted data and audited carefully in the context of collaborative inference. Code is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.16236 — 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 2026-10-18T19:02:44.159Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).