Research‎ > ‎Publications‎ > ‎

Practical privacy preserving collaborative filtering on the Google App Engine

Anirban Basu, Jaideep Vaidya, Hiroaki Kikuchi and Theo Dimitrakos

In: Computer Security Symposium (CSS), Niigata, Japan.

Year: 2011

Abstract: With rating-based collaborative filtering (CF) one can predict the rating that a user will give to an item, derived from the ratings of other items given by other users. However, preserving privacy of rating data from individual users is a significant challenge. Many privacy preserving schemes have, so far, been proposed, such as our earlier work on extending the well known weighted Slope One predictor. However, many such theoretically feasible schemes face practical implementation difficulties on real world public cloud computing platforms. In this paper, we re-visit the generalised problem of privacy preserving collaborative filtering and demonstrate an approach and a realistic implementation on the specialised Software-as-a-Service (SaaS) construction Platform-as-a-Service (PaaS) cloud offering -- the Google App Engine for Java (GAE/J).

Fulltext: PDF (Note that this is a stripped down version of the IEEE Cloudcom 2011 paper submitted to this Japanese domestic symposium. For the full paper, please see the IEEE Cloudcom 2011 version.)

Presentation: PDF

Demo: See http://gaejppcf.appspot.com (Google App Engine). Although originally planned to be used on the Google App Engine, hence the name 'gaejppcf' (for Google App Engine for Java -- Privacy Preserving Collaborative Filtering), we are also in the process of deploying it on Amazon Web Services. See http://gaejppcf.elasticbeanstalk.com (Amazon Elastic Beanstalk).
Comments