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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Fairness in machine learning (ML) is an ever-growing field of research due tothe manifold potential for harm from algorithmic discrimination. To preventsuch harm, a large body of literature develops new approaches to quantifyfairness. Here, we investigate how one can divert the quantification offairness by describing a practice we call "fairness hacking" for the purpose ofshrouding unfairness in algorithms. This impacts end-users who rely on learningalgorithms, as well as the broader community interested in fair AI practices.We introduce two different categories of fairness hacking in reference to theestablished concept of p-hacking. The first category, intra-metric fairnesshacking, describes the misuse of a particular metric by adding or removingsensitive attributes from the analysis. In this context, countermeasures thathave been developed to prevent or reduce p-hacking can be applied to similarlyprevent or reduce fairness hacking. The second category of fairness hacking isinter-metric fairness hacking. Inter-metric fairness hacking is the search fora specific fair metric with given attributes. We argue that countermeasures toprevent or reduce inter-metric fairness hacking are still in their infancy.Finally, we demonstrate both types of fairness hacking using real datasets. Ourpaper intends to serve as a guidance for discussions within the fair MLcommunity to prevent or reduce the misuse of fairness metrics, and thus reduceoverall harm from ML applications.

Fairness Hacking: The Malicious Practice of Shrouding Unfairness in Algorithms