Abstract | ||
---|---|---|
Fairness by decision-makers is believed to be auditable by third parties. In this study, we show that this is not always true. consider the following scenario. Imagine a decision-maker who discloses a subset of his dataset with decisions to make his decisions auditable. If he is corrupt, and he deliberately selects a subset that looks fair even though the overall decision is unfair, can we identify this decision-makeru0027s fraud? answer this question negatively. We first propose a sampling method that produces a subset whose distribution is biased from the original (to pretend to be fair); however, its differentiation from uniform sampling is difficult. We call such a sampling method as stealthily biased sampling, which is formulated as a Wasserstein distance minimization problem, and is solved through a minimum-cost flow computation. We proved that the stealthily biased sampling minimizes an upper-bound of the indistinguishability. We conducted experiments to see that the stealthily biased sampling is, in fact, difficult to detect. |
Year | Venue | DocType |
---|---|---|
2019 | arXiv: Machine Learning | Journal |
Volume | Citations | PageRank |
abs/1901.08291 | 0 | 0.34 |
References | Authors | |
7 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kazuto Fukuchi | 1 | 13 | 8.48 |
Satoshi Hara | 2 | 0 | 0.68 |
Takanori Maehara | 3 | 1 | 1.37 |