Newest papers

PRICE: Privacy-Preserving Image Classification in Mobile Edge-Cloud Computing with Homomorphic Encryption

Duc-Huy Nguyen, Bui Duc Manh, Chi-Hieu Nguyen, Dinh Thai Hoang, Diep N. Nguyen, Van-Dinh Nguyen, Quoc‐Viet Pham · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.25286 · cited by 0 works (OpenAlex) · open-access PDF

French

Extomorphic pay cryptation (HE) permet des calculs sur les données cryptées plus faibles; cependant, les pipelines d'inférence basées sur HE existantes entraînent de nombreuses applications d'IA mobiles, mais la transmission d'images brutes dans le nuage soulève des préoccupations importantes en matière de confidentialité. L'homomorphic pay cryptation (HE) permet des calculs sur les données cryptées plus faibles; cependant, les pipelines d'inférence basées sur HE existantes entraînent une latence interdite de trois niveaux et une superposition computationnelle, limitant leur faisabilité pour les systèmes mobiles sensibles à la latence. Ce document traite de la façon dont l'extraction de caractéristiques légères en plaintex est possible dans les envir

Machine translation (Meta M2M100); the English original follows.

Abstract

Cloud-assisted image classification enables many mobile AI applications, but transmitting raw images to the cloud raises significant privacy concerns. Homomorphic encryption (HE) allows computation over encrypted data; however, existing end-to-end HE-based inference pipelines incur prohibitive latency and computational overhead, limiting their feasibility for latency-sensitive mobile systems. This paper addresses how to enable efficient encrypted image classification in mobile edge-cloud environments without sacrificing accuracy. We propose PRICE, a three-tier edge-cloud architecture that partitions deep neural network inference between a trusted edge and an untrusted cloud. The edge performs lightweight feature extraction in plaintext, while only compact embeddings are encrypted using the Cheon-Kim-Kim-Song (CKKS) scheme and offloaded to the cloud for encrypted final-layer inference. This design avoids homomorphic evaluation of deep backbone layers, significantly reducing computation depth, ciphertext size, and end-to-end latency. To further improve efficiency, we develop RowHyDiag, a row-packed hybrid diagonal encoding with hoisted-rotation-aware encrypted matrix-vector computation, which minimizes rotation operations and improves slot utilization. Extensive experiments on real devices across five datasets demonstrate that, under the evaluated 128-bit-security configurations, RowHyDiag achieves up to 31.8$\times$ faster cloud inference, 85.3$\times$ fewer rotations, and 83.0$\times$ lower setup payload than the conventional Halevi-Shoup diagonal method. RowHyDiag also outperforms the PEGASUS linear-transformation baseline, providing 1.1-4.5$\times$ faster cloud inference and 1.2-3.4$\times$ lower setup payload. The results show that PRICE enables deployment-ready, low-latency encrypted inference for mobile edge-cloud systems under a trusted-edge threat model.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Homomorphic encryption, Encryption, Cloud computing, Ciphertext, Payload (computing)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange