Verifying Individual Fairness in Machine Learning Models

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.

[1]  Timothy A. Mann,et al.  On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Models , 2018, ArXiv.

[2]  Jean B. Lasserre,et al.  Global Optimization with Polynomials and the Problem of Moments , 2000, SIAM J. Optim..

[3]  Matthew Mirman,et al.  Fast and Effective Robustness Certification , 2018, NeurIPS.

[4]  Russ Tedrake,et al.  Evaluating Robustness of Neural Networks with Mixed Integer Programming , 2017, ICLR.

[5]  Pushmeet Kohli,et al.  A Dual Approach to Scalable Verification of Deep Networks , 2018, UAI.

[6]  Rüdiger Ehlers,et al.  Formal Verification of Piece-Wise Linear Feed-Forward Neural Networks , 2017, ATVA.

[7]  Aditi Raghunathan,et al.  Semidefinite relaxations for certifying robustness to adversarial examples , 2018, NeurIPS.

[8]  Pushmeet Kohli,et al.  Verification of Non-Linear Specifications for Neural Networks , 2019, ICLR.

[9]  Jeffrey D. Ullman,et al.  Introduction to Automata Theory, Languages and Computation , 1979 .

[10]  Yuriy Brun,et al.  Fairness testing: testing software for discrimination , 2017, ESEC/SIGSOFT FSE.

[11]  Junfeng Yang,et al.  Efficient Formal Safety Analysis of Neural Networks , 2018, NeurIPS.

[12]  J. Zico Kolter,et al.  Provable defenses against adversarial examples via the convex outer adversarial polytope , 2017, ICML.

[13]  Yizheng Chen,et al.  MixTrain: Scalable Training of Formally Robust Neural Networks , 2018, ArXiv.

[14]  Toniann Pitassi,et al.  Fairness through awareness , 2011, ITCS '12.

[15]  Mark Harman,et al.  Machine Learning Testing: Survey, Landscapes and Horizons , 2019, IEEE Transactions on Software Engineering.

[16]  Diptikalyan Saha,et al.  Black box fairness testing of machine learning models , 2019, ESEC/SIGSOFT FSE.

[17]  Cho-Jui Hsieh,et al.  Efficient Neural Network Robustness Certification with General Activation Functions , 2018, NeurIPS.

[18]  Armando Solar-Lezama,et al.  Probabilistic verification of fairness properties via concentration , 2018, Proc. ACM Program. Lang..

[19]  Cho-Jui Hsieh,et al.  A Convex Relaxation Barrier to Tight Robustness Verification of Neural Networks , 2019, NeurIPS.

[20]  Matt J. Kusner,et al.  Counterfactual Fairness , 2017, NIPS.

[21]  Mykel J. Kochenderfer,et al.  Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks , 2017, CAV.

[22]  J. Shohat,et al.  The problem of moments , 1943 .

[23]  D. Hilbert,et al.  Ueber die Darstellung definiter Formen als Summe von Formenquadraten , 1888 .

[24]  Aws Albarghouthi,et al.  FairSquare: probabilistic verification of program fairness , 2017, Proc. ACM Program. Lang..

[25]  Swarat Chaudhuri,et al.  AI2: Safety and Robustness Certification of Neural Networks with Abstract Interpretation , 2018, 2018 IEEE Symposium on Security and Privacy (SP).

[26]  Pushmeet Kohli,et al.  A Unified View of Piecewise Linear Neural Network Verification , 2017, NeurIPS.

[27]  J. Lasserre.  An Introduction to Polynomial and Semi-Algebraic Optimization , 2015 .

[28]  Mykel J. Kochenderfer,et al.  Algorithms for Verifying Deep Neural Networks , 2019, Found. Trends Optim..

[29]  Sudipta Chattopadhyay,et al.  Automated Directed Fairness Testing , 2018, 2018 33rd IEEE/ACM International Conference on Automated Software Engineering (ASE).

[30]  Christopher T. Lowenkamp,et al.  False Positives, False Negatives, and False Analyses: A Rejoinder to "Machine Bias: There's Software Used across the Country to Predict Future Criminals. and It's Biased against Blacks" , 2016 .

[31]  Junfeng Yang,et al.  Formal Security Analysis of Neural Networks using Symbolic Intervals , 2018, USENIX Security Symposium.

[32]  Timon Gehr,et al.  An abstract domain for certifying neural networks , 2019, Proc. ACM Program. Lang..

[33]  N. Z. Shor.  Class of global minimum bounds of polynomial functions , 1987 .

[34]  Manfred Morari,et al.  Safety Verification and Robustness Analysis of Neural Networks via Quadratic Constraints and Semidefinite Programming , 2019, ArXiv.

[35]  P. Parrilo.  Structured semidefinite programs and semialgebraic geometry methods in robustness and optimization , 2000 .

[36]  Matthew Mirman,et al.  Differentiable Abstract Interpretation for Provably Robust Neural Networks , 2018, ICML.