The Impact of Differential Privacy on Group Disparity Mitigation

Victor Hansen, Atula Neerkaje, Ramit Sawhney, Lucie Flek, Anders Søgaard


Abstract
The performance cost of differential privacy has, for some applications, been shown to be higher for minority groups; fairness, conversely, has been shown to disproportionally compromise the privacy of members of such groups. Most work in this area has been restricted to computer vision and risk assessment. In response, we evaluate the impact of differential privacy on fairness across four diverse tasks, focusing on how attempts to mitigate privacy violations and between-group performance differences interact: Does privacy inhibit attempts to ensure fairness? To this end, we train (𝜀,𝛿)-differentially private models with empirical risk minimization and group distributionally robust training objectives. Consistent with previous findings, we find that differential privacy increases between-group performance differences in the baseline setting; more interestingly, differential privacy reduces between-group performance differences in the robust setting. We explain this by interpreting differential privacy as regularization.
Anthology ID:
2024.findings-naacl.249
Volume:
Findings of the Association for Computational Linguistics: NAACL 2024
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3952–3965
Language:
URL:
https://aclanthology.org/2024.findings-naacl.249
DOI:
10.18653/v1/2024.findings-naacl.249
Bibkey:
Cite (ACL):
Victor Hansen, Atula Neerkaje, Ramit Sawhney, Lucie Flek, and Anders Søgaard. 2024. The Impact of Differential Privacy on Group Disparity Mitigation. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 3952–3965, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
The Impact of Differential Privacy on Group Disparity Mitigation (Hansen et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-naacl.249.pdf