PProx: efficient privacy for recommendation-as-a-service - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

PProx: efficient privacy for recommendation-as-a-service

Résumé

We present PProx, a system preventing recommendation-as-a-service (RaaS) providers from accessing sensitive data about the users of applications leveraging their services. PProx does not impact recommendations accuracy, is compatible with arbitrary recommendation algorithms, and has minimal deployment requirements. Its design combines two proxying layers directly running inside SGX enclaves at the RaaS provider side. These layers transparently pseudonymize users and items and hide links between the two, and PProx privacy guarantees are robust even to the corruption of one of these enclaves. We integrated PProx with the Harness recommendation engine and evaluated it on a 27-node cluster. Our results indicate its ability to withstand a high number of requests with low end-to-end latency, horizontally scaling up to match increasing workloads of recommendations. CCS Concepts • Security and privacy;
Fichier principal
Vignette du fichier
shepherd (1).pdf (1.38 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03752290 , version 1 (16-08-2022)

Identifiants

Citer

Guillaume Rosinosky, Simon da Silva, Sonia Ben Mokhtar, Daniel Négru, Laurent Réveillère, et al.. PProx: efficient privacy for recommendation-as-a-service. Middleware '21: 22nd International Middleware Conference, Dec 2021, Québec, Canada. pp.14-26, ⟨10.1145/3464298.3476130⟩. ⟨hal-03752290⟩
29 Consultations
203 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More