Verifying Individual Fairness in Machine Learning Models
arXiv:2006.11737
Abstract
We consider the problem of whether a given decision model, working with structured data, has individual fairness. Following the work of Dwork, a model is individually biased (or unfair) if there is a pair of valid inputs which are close to each other (according to an appropriate metric) but are treated differently by the model (different class label, or large difference in output), and it is unbiased (or fair) if no such pair exists. Our objective is to construct verifiers for proving individual fairness of a given model, and we do so by considering appropriate relaxations of the problem. We construct verifiers which are sound but not complete for linear classifiers, and kernelized polynomial/radial basis function classifiers. We also report the experimental results of evaluating our proposed algorithms on publicly available datasets.
An extended version of the paper accepted at UAI 2020, 12 pages, code is available at https://github.com/philips-george/ifv-uai-2020
References in corpus (11)
- Counterfactual Fairness
- Provable defenses against adversarial examples via the convex outer adversarial polytope
- Fairness Testing: Testing Software for Discrimination
- Evaluating Robustness of Neural Networks with Mixed Integer Programming
- On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Models
- Semidefinite relaxations for certifying robustness to adversarial examples
- Efficient Formal Safety Analysis of Neural Networks
- A Unified View of Piecewise Linear Neural Network Verification
- A Convex Relaxation Barrier to Tight Robustness Verification of Neural Networks
- Machine Learning Testing: Survey, Landscapes and Horizons
- Verification of Non-Linear Specifications for Neural Networks