cs.LGNov 11, 2026

Robustness Within a Fairness Budget: Parity Frontiers and Equal-Opportunity Reversal

Authors: Pablo Rivas, Jeremy Frank

Organizations: Department of Computing Technology, Marist University Poughkeepsie, NY 12601, USA

Abstract

Adversarial training protects predictive performance under attack but does not determine how decisions are distributed across protected groups. We formulate binary classification as projected gradient descent (PGD) adversarial-risk minimization under a squared soft demographic-parity (DP) budget, optimized with projected multiplier and one-sided penalty updates. On Adult Income, using the binary sex field supplied by the benchmark for group auditing but excluding it from prediction, we test logistic regression and a one-hidden-layer multilayer perceptron (MLP) across three paired seeds, four PGD strengths, and five budgets. At ε=0.3\varepsilon=0.3, PGD training improves balanced accuracy over empirical-risk minimization (ERM) by 7.777.77 and 11.4511.45 percentage points and removes 85.7%85.7\% and 89.5%89.5\% of attack-induced growth in hard demographic-parity difference (DPD). At the representative interior value τ=0.015τ=0.015, constrained training cuts DPD relative to PGD training by 52.2%52.2\% and 49.2%49.2\%, while remaining 3.183.18 and 8.348.34 balanced-accuracy points above ERM. Across all eight seed-averaged model-attack paths, the sampled budget path strictly orders DPD and accuracy and reverses mean signed equal-opportunity difference (EOpp). A rate theorem gives the exact true-positive-rate shift required for reversal, and the measured group rates satisfy it. Within this controlled feature-space study, robustness and parity admit useful joint operating points, but one fairness metric cannot replace a full group-rate audit.

Figures & tables

Appendix figures & tables16 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Directly Optimizing Mean Demographic Parity for Nonlinear Regression

    Jul 6, 2026Ieva Petrulionyte, Julien Mairal, Michael ArbelAlgorithmic FairnessGroup Fairness