Privacy-Preserving Distributed Collaborative Filtering

Abstract : We propose a new mechanism to preserve privacy while lever-aging user profiles in distributed recommender systems. Our mechanism relies on two contributions: (i) an original obfuscation scheme, and (ii) a randomized dissemination protocol. We show that our obfuscation scheme hides the exact profiles of users without significantly decreasing their utility for recommendation. In addition, we precisely characterize the conditions that make our randomized dissemination protocol differentially private. We compare our mechanism with a non-private as well as with a fully private alternative. We consider a real dataset from a user survey and report on simulations as well as planetlab experiments. We dissect our results in terms of accuracy and privacy trade-offs, bandwidth consumption , as well as resilience to a censorship attack. In short, our extensive evaluation shows that our twofold mechanism provides a good trade-off between privacy and accuracy, with little overhead and high resilience.
Complete list of metadatas

Cited literature [24 references]  Display  Hide  Download

https://hal.inria.fr/hal-01251314
Contributor : Davide Frey <>
Submitted on : Tuesday, January 5, 2016 - 11:57:32 PM
Last modification on : Thursday, April 18, 2019 - 5:14:05 PM
Long-term archiving on : Thursday, April 7, 2016 - 3:43:02 PM

File

main.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01251314, version 1

Citation

Antoine Boutet, Davide Frey, Rachid Guerraoui, Arnaud Jégou, Anne-Marie Kermarrec. Privacy-Preserving Distributed Collaborative Filtering. Computing, Springer Verlag, 2016, Special Issue on NETYS 2014, 98 (8). ⟨hal-01251314⟩

Share

Metrics

Record views

2751

Files downloads

380