Feasibility of a privacy preserving collaborative filtering scheme on the Google App Engine: a performance case study

Authors:
Anirban Basu;Jaideep Vaidya;Theo Dimitrakos;Hiroaki Kikuchi
Affiliations:
Tokai University, Takanawa, Minato-ku, Tokyo, Japan;The State University of New Jersey, Newark, New Jersey;British Telecom, Martlesham Heath, Ipswitch, UK;Tokai University, Kanagawa, Japan, Kanagawa, Japan
Venue:
Proceedings of the 27th Annual ACM Symposium on Applied Computing
Year:
2012

Citing 5
Cited 0

A Generalisation, a Simplification and Some Applications of Paillier's Probabilistic Public-Key System

PKC '01 Proceedings of the 4th International Workshop on Practice and Theory in Public Key Cryptography: Public Key Cryptography
Tools for privacy preserving distributed data mining

ACM SIGKDD Explorations Newsletter
MapReduce: simplified data processing on large clusters

Communications of the ACM - 50th anniversary issue: 1958 - 2008
Controlling data in the cloud: outsourcing computation without outsourcing control

Proceedings of the 2009 ACM workshop on Cloud computing security
Airavat: security and privacy for MapReduce

NSDI'10 Proceedings of the 7th USENIX conference on Networked systems design and implementation

Quantified Score

Hi-index	0.00

Visualization

Abstract

The cloud is a utility computing infrastructure that has caused a paradigm shift in the way organisations requisition, allocate, and use IT resources. One big challenge is to preserve the confidentiality of information on the cloud. Most typical solutions use cryptographic techniques without considering how well suited they are to the cloud. This paper presents a performance case-study on implementing the building blocks of a privacy preserving collaborative filtering (PPCF) scheme in Java on the Google App Engine (GAE/J) cloud platform. The results show that the GAE/J in its current state exhibits serious performance bottlenecks for the chosen application scenario. This case study highlights the need for better performance from the GAE/J. It also informs the need for validating theoretical cloud security algorithms on real cloud computing platforms in which many performance expectations do not hold.