Background and Related Work on Privacy-preserving Computation of Fairness for ML Systems by@escholar

Background and Related Work on Privacy-preserving Computation of Fairness for ML Systems

tldt arrow
Read on Terminal Reader
Read this story w/o Javascript

Too Long; Didn't Read

This section delves into the crucial aspect of trust and trustworthiness in AI-based systems, introducing a framework inspired by social frameworks on trust. The focus is on auditing ML models for fairness, addressing the complexities of trust in AI solutions. It highlights the limitations of existing fairness metrics, paving the way for Fairness as a Service (FaaS), a groundbreaking and verifiable approach that ensures trustworthiness in fairness evaluations, independent of the ML model and fairness metric set.

Company Mentioned

Mention Thumbnail
featured image - Background and Related Work on Privacy-preserving Computation of Fairness for ML Systems
EScholar: Electronic Academic Papers for Scholars HackerNoon profile picture

@escholar

EScholar: Electronic Academic Papers for Scholars

We publish the best academic work (that's too often lost to peer reviews & the TA's desk) to the global tech community


Receive Stories from @escholar

react to story with heart
EScholar: Electronic Academic Papers for Scholars HackerNoon profile picture
by EScholar: Electronic Academic Papers for Scholars @escholar.We publish the best academic work (that's too often lost to peer reviews & the TA's desk) to the global tech community
Read my stories

RELATED STORIES

L O A D I N G
. . . comments & more!