Ben-Porat, O., F. Sandomirskiy, and M. Tennenholtz. “Protecting the Protected Group: Circumventing Harmful Fairness”. Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 6, May 2021, pp. 5176-84, doi:10.1609/aaai.v35i6.16654.