Fairness in the Eyes of the Data: Certifying Machine-Learning Models

Shahar Segal, Yossi Adi, Benny Pinkas, Carsten Baum, Chaya Ganesh, Joseph Keshet

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

15 Scopus citations

Abstract

We present a framework that allows to certify the fairness degree of a model based on an interactive and privacy-preserving test. The framework verifies any trained model, regardless of its training process and architecture. Thus, it allows us to evaluate any deep learning model on multiple fairness definitions empirically. We tackle two scenarios, where either the test data is privately available only to the tester or is publicly known in advance, even to the model creator. We investigate the soundness of the proposed approach using theoretical analysis and present statistical guarantees for the interactive test. Finally, we provide a cryptographic technique to automate fairness testing and certified inference with only black-box access to the model at hand while hiding the participants' sensitive data.

Original languageAmerican English
Title of host publicationAIES 2021 - Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society
PublisherAssociation for Computing Machinery, Inc
Pages926-935
Number of pages10
ISBN (Electronic)9781450384735
DOIs
StatePublished - 21 Jul 2021
Event4th AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society, AIES 2021 - Virtual, Online, United States
Duration: 19 May 202121 May 2021

Publication series

NameAIES 2021 - Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society

Conference

Conference4th AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society, AIES 2021
Country/TerritoryUnited States
CityVirtual, Online
Period19/05/2121/05/21

Bibliographical note

Publisher Copyright:
© 2021 ACM.

Keywords

  • cryptography
  • fairness
  • machine-learning
  • privacy

Fingerprint

Dive into the research topics of 'Fairness in the Eyes of the Data: Certifying Machine-Learning Models'. Together they form a unique fingerprint.

Cite this