eprintid: 19563
rev_number: 2
eprint_status: archive
userid: 1
dir: disk0/00/01/95/63
datestamp: 2024-06-04 14:19:18
lastmod: 2024-06-04 14:19:18
status_changed: 2024-06-04 14:15:18
type: article
metadata_visibility: show
creators_name: Mamman, H.
creators_name: Basri, S.
creators_name: Balogun, A.O.
creators_name: Imam, A.A.
creators_name: Kumar, G.
creators_name: Capretz, L.F.
title: BiasTrap: Runtime Detection of Biased Prediction in Machine Learning Systems
ispublished: pub
note: cited By 0
abstract: Machine Learning (ML) systems are now widely used across various fields such as hiring, healthcare, and criminal justice, but they are prone to unfairness and discrimination, which can have serious consequences for individuals and society. Although various fairness testing methods have been developed to tackle this issue, they lack the mechanism to monitor ML system behaviour at runtime continuously. This study proposes a runtime verification tool called BiasTrap to detect and prevent discrimination in ML systems. The tool combines data augmentation and bias detection components to create and analyse instances with different sensitive attributes, enabling the detection of discriminatory behaviour in the ML model. The simulation results demonstrate that BiasTrap can effectively detect discriminatory behaviour in ML models trained on different datasets using various algorithms. Therefore, BiasTrap is a valuable tool for ensuring fairness in ML systems in real time. © 2024, Semarak Ilmu Publishing. All rights reserved.
date: 2024
official_url: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85186941720&doi=10.37934%2faraset.40.2.127139&partnerID=40&md5=616198f856a25599965ae5904ac2dcb2
id_number: 10.37934/araset.40.2.127139
full_text_status: none
publication: Journal of Advanced Research in Applied Sciences and Engineering Technology
volume: 40
number: 2
pagerange: 127-139
refereed: TRUE
citation:   Mamman, H. and Basri, S. and Balogun, A.O. and Imam, A.A. and Kumar, G. and Capretz, L.F.  (2024) BiasTrap: Runtime Detection of Biased Prediction in Machine Learning Systems.  Journal of Advanced Research in Applied Sciences and Engineering Technology, 40 (2).  pp. 127-139.