Auditing black-box models for indirect influence

Philip Adler, Casey Falk, Sorelle A. Friedler, Tionney Nix, Gabriel Rybeck, Carlos Scheidegger, Brandon Smith, Suresh Venkatasubramanian

Research output: Contribution to journalArticlepeer-review

138 Scopus citations


Data-trained predictive models see widespread use, but for the most part they are used as black boxes which output a prediction or score. It is therefore hard to acquire a deeper understanding of model behavior and in particular how different features influence the model prediction. This is important when interpreting the behavior of complex models or asserting that certain problematic attributes (such as race or gender) are not unduly influencing decisions. In this paper, we present a technique for auditing black-box models, which lets us study the extent to which existing models take advantage of particular features in the data set, without knowing how the models work. Our work focuses on the problem of indirect influence: how some features might indirectly influence outcomes via other, related features. As a result, we can find attribute influences even in cases where, upon further direct examination of the model, the attribute is not referred to by the model at all. Our approach does not require the black-box model to be retrained. This is important if, for example, the model is only accessible via an API, and contrasts our work with other methods that investigate feature influence such as feature selection. We present experimental evidence for the effectiveness of our procedure using a variety of publicly available data sets and models. We also validate our procedure using techniques from interpretable learning and feature selection, as well as against other black-box auditing procedures. To further demonstrate the effectiveness of this technique, we use it to audit a black-box recidivism prediction algorithm.

Original languageEnglish (US)
Pages (from-to)95-122
Number of pages28
JournalKnowledge and Information Systems
Issue number1
StatePublished - Jan 1 2018


  • Algorithmic accountability
  • Black-box auditing
  • Deep learning
  • Discrimination-aware data mining
  • Feature influence
  • Interpretable machine learning

ASJC Scopus subject areas

  • Software
  • Information Systems
  • Human-Computer Interaction
  • Hardware and Architecture
  • Artificial Intelligence


Dive into the research topics of 'Auditing black-box models for indirect influence'. Together they form a unique fingerprint.

Cite this