English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Auditing fairness of decision-makers is now in high demand. To respond tothis social demand, several fairness auditing tools have been developed. Thefocus of this study is to raise an awareness of the risk of maliciousdecision-makers who fake fairness by abusing the auditing tools and therebydeceiving the social communities. The question is whether such a fraud of thedecision-maker is detectable so that the society can avoid the risk of fakefairness. In this study, we answer this question negatively. We specificallyput our focus on a situation where the decision-maker publishes a benchmarkdataset as the evidence of his/her fairness and attempts to deceive a personwho uses an auditing tool that computes a fairness metric. To assess the(un)detectability of the fraud, we explicitly construct an algorithm, thestealthily biased sampling, that can deliberately construct an evil benchmarkdataset via subsampling. We show that the fraud made by the stealthily basedsampling is indeed difficult to detect both theoretically and empirically.

Faking Fairness via Stealthily Biased Sampling