• Classified by Research Topic • Sorted by Date • Classified by Publication Type •
Justicia: A Stochastic SAT Approach to Formally Verify Fairness.
Bishwamittra Ghosh, Debabrota Basu and Kuldeep S. Meel.
In Proceedings of AAAI Conference on Artificial Intelligence (AAAI), February 2021.
As a technology ML is oblivious to societal good or bad, and thus, the field of fair machine learning has stepped up to propose multiple mathematical definitions, algorithms, and systems to ensure different notions of fairness in ML applications. Given the multitude of propositions, it has become imperative to formally verify the fairness metrics satisfied by different algorithms on different datasets. In this paper, we propose a stochastic satisfiability (SSAT) framework, Justicia, that formally verifies different fairness measures of supervised learning algorithms with respect to the underlying data distribution. We instantiate Justicia on multiple classification and bias mitigation algorithms, and datasets to verify different fairness metrics, such as disparate impact, statistical parity, and equalized odds. Justicia is scalable, accurate, and operates on non-Boolean and compound sensitive attributes unlike existing distribution-based verifiers, such as FairSquare and VeriFair. Being distribution-based by design, Justicia is more robust than the verifiers, such as AIF360, that operate on specific test samples. We also theoretically bound the finite-sample error of the verified fairness measure.
@inproceedings{GBM21,
title={Justicia: A Stochastic SAT Approach to Formally Verify Fairness},
author={Ghosh, Bishwamittra and Basu, Debabrota and Meel, Kuldeep S.},
booktitle=AAAI,
month=feb,
year={2021},
bib2html_rescat={Formal Methods 4 ML},
bib2html_pubtype={Refereed Conference},
bib2html_dl_pdf={../Papers/aaai21-gbm.pdf},
abstract={
As a technology ML is oblivious to societal good or bad,
and thus, the field of fair machine learning has stepped up to
propose multiple mathematical definitions, algorithms, and
systems to ensure different notions of fairness in ML applications.
Given the multitude of propositions, it has become
imperative to formally verify the fairness metrics satisfied by
different algorithms on different datasets. In this paper, we
propose a stochastic satisfiability (SSAT) framework, Justicia,
that formally verifies different fairness measures of supervised
learning algorithms with respect to the underlying data distribution.
We instantiate Justicia on multiple classification and
bias mitigation algorithms, and datasets to verify different fairness
metrics, such as disparate impact, statistical parity, and
equalized odds. Justicia is scalable, accurate, and operates on
non-Boolean and compound sensitive attributes unlike existing
distribution-based verifiers, such as FairSquare and VeriFair.
Being distribution-based by design, Justicia is more robust
than the verifiers, such as AIF360, that operate on specific test
samples. We also theoretically bound the finite-sample error
of the verified fairness measure.
},
}
Generated by bib2html.pl (written by Patrick Riley with layout from Sanjit A. Seshia ) on Tue Apr 28, 2026 01:27:21