PProx : efficient privacy for recommendation-as-a-service
(2021) Middleware ’21: 22nd International Middleware Conference — Location: Québec city Canada
Files
main.pdf
Open Access - Adobe PDF
- 1.23 MB
Details
- Authors
- Abstract
- 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 Harness's Universal Recommender 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.
- Affiliations
Citations
Rosinosky, G., Da Silva, S., Ben Mokhtar, S., Négru, D., Réveillère, L., & Riviere, E. (2021). PProx : efficient privacy for recommendation-as-a-service. Middleware ’21: Proceedings of the 22nd International Middleware Conference. Published. Middleware ’21: 22nd International Middleware Conference, Québec city Canada. https://doi.org/10.1145/3464298.3476130