Anti-discrimination Analysis Using Privacy Attack Strategies

  • Salvatore Ruggieri
  • Sara Hajian
  • Faisal Kamiran
  • Xiangliang Zhang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8725)

Abstract

Social discrimination discovery from data is an important task to identify illegal and unethical discriminatory patterns towards protected-by-law groups, e.g., ethnic minorities. We deploy privacy attack strategies as tools for discrimination discovery under hard assumptions which have rarely tackled in the literature: indirect discrimination discovery, privacy-aware discrimination discovery, and discrimination data recovery. The intuition comes from the intriguing parallel between the role of the anti-discrimination authority in the three scenarios above and the role of an attacker in private data publishing. We design strategies and algorithms inspired/based on Frèchet bounds attacks, attribute inference attacks, and minimality attacks to the purpose of unveiling hidden discriminatory practices. Experimental results show that they can be effective tools in the hands of anti-discrimination authorities.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2014

Authors and Affiliations

  • Salvatore Ruggieri
    • 1
  • Sara Hajian
    • 2
  • Faisal Kamiran
    • 3
  • Xiangliang Zhang
    • 4
  1. 1.Università di PisaItaly
  2. 2.Universitat Rovira i VirgiliSpain
  3. 3.Information TechnologyUniversity of the PunjabPakistan
  4. 4.King Abdullah University of Science and TechnologySaudi Arabia

Personalised recommendations