Challenging Differential Privacy:The Case of Non-interactive Mechanisms

  • Raghavendran Balu
  • Teddy Furon
  • Sébastien Gambs
Conference paper

DOI: 10.1007/978-3-319-11212-1_9

Part of the Lecture Notes in Computer Science book series (LNCS, volume 8713)
Cite this paper as:
Balu R., Furon T., Gambs S. (2014) Challenging Differential Privacy:The Case of Non-interactive Mechanisms. In: Kutyłowski M., Vaidya J. (eds) Computer Security - ESORICS 2014. ESORICS 2014. Lecture Notes in Computer Science, vol 8713. Springer, Cham

Abstract

In this paper, we consider personalized recommendation systems in which before publication, the profile of a user is sanitized by a non-interactive mechanism compliant with the concept of differential privacy. We consider two existing schemes offering a differentially private representation of profiles: BLIP (BLoom-and-flIP) and JLT (Johnson-Lindenstrauss Transform). For assessing their security levels, we play the role of an adversary aiming at reconstructing a user profile. We compare two inference attacks, namely single and joint decoding. The first one decides of the presence of a single item in the profile, and sequentially explores all the item set. The latter strategy decides whether a subset of items is likely to be the user profile, and considers all the possible subsets. Our contributions are a theoretical analysis as well as a practical implementation of both attacks, which were evaluated on datasets of real user profiles. The results obtained clearly demonstrates that joint decoding is the most powerful attack, while also giving useful insights on how to set the differential privacy parameter ε.

Keywords

Differential privacy Joint decoding 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Raghavendran Balu
    • 1
  • Teddy Furon
    • 1
  • Sébastien Gambs
    • 1
    • 2
  1. 1.Inria Rennes Bretagne-AtlantiqueFrance
  2. 2.Université de Rennes 1 / IRISAFrance

Personalised recommendations