Qiang Tang

BRAIDS: Boosting Security and Efficiency in Recommender Systems (FNR CORE junior track)

As e-commerce websites began to develop, a pressing need emerged for providing recommendations derived from filtering the whole range of available alternatives. Users were finding it very difficult to make the most appropriate choices from the immense variety of items (products and services) that these websites were offering. Take an online book store as an example, going through the lengthy book catalogue not only wastes a lot of time but also frequently overwhelms users and leads them to make poor decisions. As such, the availability of choices, instead of producing a benefit, started to decrease users’ well-being. Eventually, this need led to the development of recommender systems (or, recommendation systems). Informally, recommender systems are a subclass of information filtering system that seek to predict the 'rating' or 'preference' that a user would give to an item (such as music, book, or movie) or social element (e.g. people or group) they had not yet considered, using a model built from the characteristics of items and/or users. In order to compute recommendations for users, a recommendation service provider needs to collect a lot of personal data from its customers, such as ratings, transaction history, and location. This makes recommender systems a double-edged sword. On one side users get better recommendations when they reveal more personal data, but on the flip side they sacrifice more privacy if they do so.

In this project, we aim at solving the utility-privacy dilemma, namely we want to protect users’ privacy to the maximal extent while still enabling them to receive accurate recommendations. We will investigate the realistic privacy notions for recommender systems, and invent privacy-enhancing technologies that allow recommendations to be generated in a secure manner (e.g. generated on encrypted data). We expect that the resulting technologies can also be used in other related services, e.g. privacy-preserving event correlation between different ISPs (Internet Service Providers).

Project-related Publications

Methods for Efficient Homomorphic Integer Polynomial Evaluation based on GSW FHE (PDF)
Husen Wang, Qiang Tang
Cryptology ePrint Archive: Report 2016/488
Cryptographic Solutions for Credibility and Liability Issues of Genomic Data (PDF)
Erman Ayday, Qiang Tang, Arif Yilmaz
TDSC - IEEE Transactions on Dependable and Secure Computing (IEEE)
Cryptology ePrint Archive: Report 2016/478
Differentially Private Neighborhood-based Recommender Systems (PDF)
Jun Wang, Qiang Tang
IFIP SEC (Springer)
Privacy-preserving Hybrid Recommender System (PDF)
Qiang Tang, Husen Wang
AsiaCCS SCC workshop (ACM)
To Cheat or Not to Cheat - A Game-Theoretic Analysis of Outsourced Computation Verification (PDF)
Balazs Pejo, Qiang Tang
AsiaCCS SCC workshop (ACM)
Privacy-preserving friendship-based recommender systems (PDF)
Qiang Tang, Jun Wang
TDSC - IEEE Transactions on Dependable and Secure Computing (IEEE)
Protect both integrity and confidentiality in outsourcing collaborative filtering computations (PDF)
Qiang Tang, Balazs Pejo, Husen Wang
CLOUD - 2016 IEEE International Conference on Cloud Computing (IEEE)
A probabilistic view of neighborhood-based recommendation methods (PDF)
Jun Wang, Qiang Tang
CLOUDMINE - ICDM-2016 Workshop on Data Mining Systems and their Applications on the Cloud (IEEE)
(poster) Game-theoretic framework for integrity verification in computation outsourcing (PDF)
Qiang Tang, Balazs Pejo
Gamesec - 2016 Conference on Decision and Game Theory for Security (Springer)
Privacy-Preserving Context-Aware Recommender Systems: Analysis and New Solutions (PDF)
Qiang Tang, Jun Wang
ESORICS - 20th European Symposium on Research in Computer Security (Springer)
Key Recovery Attacks Against NTRU-Based Somewhat Homomorphic Encryption Schemes (PDF)
Massimo Chenal, Qiang Tang
ISC - Information Security - 18th International Conference (Springer)
Methods to Mitigate Risk of Composition Attack in Independent Data Publications (PDF)
Jiuyong Li, Sarowar A. Sattar, Muzammil M. Baig, Jixue Liu, Raymond Heatherly, Qiang Tang, Bradley Malin
Book chapter of Medical Data Privacy Handbook
On Key Recovery Attacks against Existing Somewhat Homomorphic Encryption Schemes (PDF)
Massimo Chenal, Qiang Tang
Latincrypt 2014 (Springer)