BiasTrap: Runtime Detection of Biased Prediction in Machine Learning Systems

Authors

  • Hussaini Mamman Department of Management and Information Technology, Abubakar Tafawa Balewa University, Bauchi, 740272, Nigeria
  • Shuib Basri Department of Computer and Information Sciences, Universiti Teknologi PETRONAS, Bandar Seri Iskandar, 32610 Perak, Malaysia
  • Abdullateef Oluwagbemiga Balogun Department of Computer and Information Sciences, Universiti Teknologi PETRONAS, Bandar Seri Iskandar, 32610 Perak, Malaysia
  • Abdullahi Abubakar Imam Department of Computer Sciences, Universiti Brunei Darussalam, BE1410, Brunei Darussalam
  • Ganesh Kumar Department of Computer and Information Sciences, Universiti Teknologi PETRONAS, Bandar Seri Iskandar, 32610 Perak, Malaysia
  • Luiz Fernando Capretz Department of Electrical and Computer Engineering, Western University, London, ON N6A 5B9, Canada

DOI:

https://doi.org/10.37934/araset.40.2.127139

Keywords:

Fairness Testing, Runtime Verification, Bias Detection, Machine Learning Systems

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 continuously monitor ML system behaviour at runtime. In this study, a runtime verification tool called BiasTrap is proposed 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.

Author Biographies

Hussaini Mamman, Department of Management and Information Technology, Abubakar Tafawa Balewa University, Bauchi, 740272, Nigeria

hussaini_21000736@utp.edu.my

Shuib Basri, Department of Computer and Information Sciences, Universiti Teknologi PETRONAS, Bandar Seri Iskandar, 32610 Perak, Malaysia

shuib_basri@utp.edu.my

Abdullateef Oluwagbemiga Balogun, Department of Computer and Information Sciences, Universiti Teknologi PETRONAS, Bandar Seri Iskandar, 32610 Perak, Malaysia

abdullateef.ob@utp.edu.my

Abdullahi Abubakar Imam, Department of Computer Sciences, Universiti Brunei Darussalam, BE1410, Brunei Darussalam

abdullahi.imam@ubd.edu.bn

Ganesh Kumar, Department of Computer and Information Sciences, Universiti Teknologi PETRONAS, Bandar Seri Iskandar, 32610 Perak, Malaysia

ganesh_17005106@utp.edu.my

Luiz Fernando Capretz, Department of Electrical and Computer Engineering, Western University, London, ON N6A 5B9, Canada

lcapretz@uwo.ca

Downloads

Published

2024-02-28

How to Cite

Hussaini Mamman, Shuib Basri, Abdullateef Oluwagbemiga Balogun, Abdullahi Abubakar Imam, Ganesh Kumar, & Luiz Fernando Capretz. (2024). BiasTrap: Runtime Detection of Biased Prediction in Machine Learning Systems. Journal of Advanced Research in Applied Sciences and Engineering Technology, 40(2), 127–139. https://doi.org/10.37934/araset.40.2.127139

Issue

Vol. 40 No. 2: October (2024)

Section

Articles