Paper 2018/911

Achieving Fair Treatment in Algorithmic Classification

Andrew Morgan and Rafael Pass


Fairness in classification has become an increasingly relevant and controversial issue as computers replace humans in many of today’s classification tasks. In particular, a subject of much recent debate is that of finding, and subsequently achieving, suitable definitions of fairness in an algorithmic context. In this work, following the work of Hardt et al. (NIPS’16), we consider and formalize the task of sanitizing an unfair classifier C into a classifier C' satisfying an approximate notion of "equalized odds", or fair treatment. Our main result shows how to take any (possibly unfair) classifier C over a finite outcome space, and transform it—-by just perturbing the output of C—according to some distribution learned by just having black-box access to samples of labeled, and previously classified, data, to produce a classifier C' that satisfies fair treatment; we additionally show that our derived classifier is near-optimal in terms of accuracy. We also experimentally evaluate the performance of our method.

Note: Full version of a paper (by the same title) to appear in TCC 2018.

Available format(s)
Publication info
A major revision of an IACR publication in TCC 2018
fairnessclassificationblack-box algorithmsfair treatmentdifferential privacy
Contact author(s)
asmorgan @ cs cornell edu
2018-10-17: last of 2 revisions
2018-09-25: received
See all versions
Short URL
Creative Commons Attribution


      author = {Andrew Morgan and Rafael Pass},
      title = {Achieving Fair Treatment in Algorithmic Classification},
      howpublished = {Cryptology ePrint Archive, Paper 2018/911},
      year = {2018},
      note = {\url{}},
      url = {}
Note: In order to protect the privacy of readers, does not use cookies or embedded third party content.