Quantifying Program Bias
Programming Languages
2017-03-08 v2 Artificial Intelligence
Abstract
With the range and sensitivity of algorithmic decisions expanding at a break-neck speed, it is imperative that we aggressively investigate whether programs are biased. We propose a novel probabilistic program analysis technique and apply it to quantifying bias in decision-making programs. Specifically, we (i) present a sound and complete automated verification technique for proving quantitative properties of probabilistic programs; (ii) show that certain notions of bias, recently proposed in the fairness literature, can be phrased as quantitative correctness properties; and (iii) present FairSquare, the first verification tool for quantifying program bias, and evaluate it on a range of decision-making programs.
Cite
@article{arxiv.1702.05437,
title = {Quantifying Program Bias},
author = {Aws Albarghouthi and Loris D'Antoni and Samuel Drews and Aditya Nori},
journal= {arXiv preprint arXiv:1702.05437},
year = {2017}
}