Skip to main content
Log in

FreeRec: an anonymous and distributed personalization architecture

  • Published:
Computing Aims and scope Submit manuscript

Abstract

We present and evaluate FreeRec, an anonymous decentralized peer-to-peer architecture, designed to bring personalization while protecting the privacy of its users. FreeRec’s decentralized approach makes it independent of any entity wishing to collect personal data about users. At the same time, its onion-routing-like gossip-based overlay protocols effectively hide the association between users and their interest profiles without affecting the quality of personalization. The core of FreeRec consists of three layers of overlay protocols: the bottom layer, rps, consists of a standard random peer sampling protocol ensuring connectivity; the middle layer, PRPS, introduces anonymity by hiding users behind anonymous proxy chains, providing mutual anonymity; finally, the top clustering layer identifies for each anonymous user, a set of anonymous nearest neighbors. We demonstrate the effectiveness of FreeRec by building a decentralized and anonymous content dissemination system. Our evaluation by simulation, our PlanetLab experiments, and our probabilistic analysis show that FreeRec effectively decouples users from their profiles without hampering the quality of personalized content delivery.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

Notes

  1. We use the term node to refer both to a user and to her machine.

  2. We use uppercase characters for public keys and lowercase for private or secret keys.

  3. Clustering is not shown for it has a similar behaviour as PRPS with a bandwidth consumption exactly twice as much as that of the PRPS due to the larger gossip size.

  4. Each PlanetLab node hosts a large number of virtual machines (slivers) that together result in high resource consumption.

References

  1. Anonymous surfing solution http://anonymouse.org/

  2. Alaggan M, Gambs S, Kermarrec AM (2012) BLIP: non-interactive differentially-private similarity computation on bloom filters. In: SSS

  3. Bakker A, van Steen M (2008) Puppetcast: a secure peer sampling protocol. In: EC2ND

  4. Bansod N, Malgi A, Choi BK, Mayo J (2008) Muon: epidemic based mutual anonymity in unstructured p2p networks. Comput Netw.

  5. Bertier M, Frey D, Guerraoui R, Kermarrec AM, Leroy V (2010) The gossple anonymous social network. In: Middleware

  6. Bortnikov E, Gurevich M, Keidar I, Kliot G, Shraer A (2008) Brahms: byzantine resilient random membership sampling. In: PODC

  7. Boutet A, Frey D, Guerraoui R, Jegou A, Kermarrec AM (2013) Privacy-preserving distributed collaborative filtering. In: Activity Report

  8. Boutet A, Frey D, Guerraoui R, Jegou A, Kermarrec AM (2013) Whatsup decentralized instant news recommender. In: IPDPS

  9. Boutet A, Frey D, Jégou A, Kermarrec AM, Ribeiro HB (2013) FreeRec: an anonymous and distributed personalization architecture. In: NETYS, Marrakesh, Maroc

  10. Canny J (2002) Collaborative filtering with privacy. In: SP

  11. Canny J (2002) Collaborative filtering with privacy via factor analysis. In: SIGIR

  12. Dingledine R, Mathewson N, Syverson P (2004) Tor: the second-generation onion router. In: USENIX Security Symposium

  13. Goldreich O (2003) Cryptography and cryptographic protocols. Distrib Comput

  14. Huang Z, Du W, Chen B (2005) Deriving private information from randomized data. In: SIGMOD

  15. Isaacman S, Ioannidis S, Chaintreau A, Martonosi M (2011) Distributed rating prediction in user generated content streams. In: RecSys

  16. Jégou A, Frey D, Boutet A, Kermarrec AM, Ribeiro HB (2013) FreeRec: an anonymous and distributed personalization architecture. Rapport technique

  17. Jelasity M, Voulgaris S, Guerraoui R, Kermarrec AM, van Steen M (2007) Gossip-based peer sampling. TOCS

  18. Jesi GP, Montresor A, van Steen M (2010) Secure peer sampling. Comput Netw

  19. Kargupta H, Datta S, Wang Q, Sivakumar K (2003) On the privacy preserving properties of random data perturbation techniques. In: ICDM

  20. Li HC, Clement A, Wong EL, Napper J, Roy I, Alvisi L, Dahlin M (2006) Bar gossip. In: OSDI

  21. Machanavajjhala A, Korolova A, Sarma AD (2011) Personalized social recommendations: accurate or private. VLDB

  22. Miller BN, Konstan JA, Riedl J (2004) Pocketlens: toward a personal recommender system. TOIS

  23. Polat H, Du W (2003) Privacy-preserving collaborative filtering using randomized perturbation techniques. In: ICDM

  24. Polat H, Du W (2005) Svd-based collaborative filtering with privacy. In: SAC

  25. Schiavoni V, Riviere E, Felber P (2011) Whisper: middleware for confidential communication in large-scale networks. In: ICDCS

  26. Singh A, Urdaneta G, van Steen M, Vitenberg R (2012) Robust overlays for privacy-preserving data dissemination over a social graph. In: ICDCS

  27. Su X, Khoshgoftaar TM (2009) A survey of collaborative filtering techniques. Adv Artif Intell

  28. van Rijsbergen CJ (1979) Information retrieval. Butterworth

  29. Voulgaris S, Gavidia D, van Steen M (2005) Cyclon: inexpensive membership management for unstructured p2p overlays. J Netw Syst Manag

  30. Voulgaris S, van Steen M (2005) Epidemic-style management of semantic overlays for content-based searching. In: Euro-Par

  31. Zhu Y, Hu Y (2004) Tap: a novel tunneling approach for anonymity in structured p2p systems. In: ICPP

  32. Zhuang L, Zhou F, Zhao BY, Rowstron A (2005) Cashmere: resilient anonymous routing. In: NSDI

Download references

Acknowledgments

This research is part-funded by the ERC Starting Grant GOSSPLE number 204742.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Antoine Boutet.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Boutet, A., Frey, D., Jégou, A. et al. FreeRec: an anonymous and distributed personalization architecture. Computing 97, 961–980 (2015). https://doi.org/10.1007/s00607-013-0377-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00607-013-0377-2

Keywords

Mathematics Subject Classification

Navigation