An official website of the United States government
Voting is used widely to identify a collective decision for a group of agents, based on their preferences. In this paper, we focus on evaluating and designing voting rules that support both the privacy of the voting agents and a notion of fairness over such agents. To do this, we introduce a novel notion of group fairness and adopt the existing notion of local differential privacy. We then evaluate the level of group fairness in several existing voting rules, as well as the trade-offs between fairness and privacy, showing that it is not possible to always obtain maximal economic efficiency with high fairness or high privacy levels. Then, we present both a machine learning and a constrained optimization approach to design new voting rules that are fair while maintaining a high level of economic efficiency. Finally, we empirically examine the effect of adding noise to create local differentially private voting rules and discuss the three-way trade-off between economic efficiency, fairness, and privacy.This paper appears in the special track on AI & Society.
more »
« less
This content will become publicly available on April 11, 2026
Fairness Issues and Mitigations in (Differentially Private) Socio-Demographic Data Processes
Statistical agencies rely on sampling techniques to collect socio-demographic data crucial for policy-making and resource allocation. This paper shows that surveys of important societal relevance introduce sampling errors that unevenly impact group-level estimates, thereby compromising fairness in downstream decisions. To address these issues, this paper introduces an optimization approach modeled on real-world survey design processes, ensuring sampling costs are optimized while maintaining error margins within prescribed tolerances. Additionally, privacy-preserving methods used to determine sampling rates can further impact these fairness issues. This paper explores the impact of differential privacy on the statistics informing the sampling process, revealing a surprising effect: not only is the expected negative effect from the addition of noise for differential privacy negligible, but also this privacy noise can in fact reduce unfairness as it positively biases smaller counts. These findings are validated over an extensive analysis using datasets commonly applied in census statistics.
more »
« less
- Award ID(s):
- 2133169
- PAR ID:
- 10649525
- Publisher / Repository:
- Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI)
- Date Published:
- Journal Name:
- Proceedings of the AAAI Conference on Artificial Intelligence
- Volume:
- 39
- Issue:
- 27
- ISSN:
- 2159-5399
- Page Range / eLocation ID:
- 28160 to 28167
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Data sets and statistics about groups of individuals are increasingly collected and released, feeding many optimization and learning algorithms. In many cases, the released data contain sensitive information whose privacy is strictly regulated. For example, in the U.S., the census data is regulated under Title 13, which requires that no individual be identified from any data released by the Census Bureau. In Europe, data release is regulated according to the General Data Protection Regulation, which addresses the control and transfer of personal data. Differential privacy has emerged as the de-facto standard to protect data privacy. In a nutshell, differentially private algorithms protect an individual’s data by injecting random noise into the output of a computation that involves such data. While this process ensures privacy, it also impacts the quality of data analysis, and, when private data sets are used as inputs to complex machine learning or optimization tasks, they may produce results that are fundamentally different from those obtained on the original data and even rise unintended bias and fairness concerns. In this talk, I will first focus on the challenge of releasing privacy-preserving data sets for complex data analysis tasks. I will introduce the notion of Constrained-based Differential Privacy (C-DP), which allows casting the data release problem to an optimization problem whose goal is to preserve the salient features of the original data. I will review several applications of C-DP in the context of very large hierarchical census data, data streams, energy systems, and in the design of federated data-sharing protocols. Next, I will discuss how errors induced by differential privacy algorithms may propagate within a decision problem causing biases and fairness issues. This is particularly important as privacy-preserving data is often used for critical decision processes, including the allocation of funds and benefits to states and jurisdictions, which ideally should be fair and unbiased. Finally, I will conclude with a roadmap to future work and some open questions.more » « less
-
Owners of data may wish to share some statistics with others, but they may be worried of privacy of the underlying data. An effective solution to this problem is to employ provable privacy techniques, such as differential privacy, to add noise to the statistics before releasing them. This protection lowers the risk of sharing sensitive data with more or less trusted data sharing partners. Unfortunately, applying differential privacy in its mathematical form requires one to fix certain numeric parameters, which involves subtle computations and expert knowledge that the data owners may lack.In this paper, we first describe a differential privacy parameter selection procedure that minimizes what lay data owners need to know. Second, we describe a user visualization and workflow that makes this procedure available for lay data owners by helping them set the level of noise appropriately to achieve a tolerable risk level. Finally, we describe a user study in which human factors professionals who were native to differential privacy were briefly trained on the concept of using differential privacy for data sharing and then used the visualization to determine an appropriate level of noise.more » « less
-
The process of data mining with differential privacy produces results that are affected by two types of noise: sampling noise due to data collection and privacy noise that is designed to prevent the reconstruction of sensitive information. In this paper, we consider the problem of designing confidence intervals for the parameters of a variety of differentially private machine learning models. The algorithms can provide confidence intervals that satisfy differential privacy (as well as the more recently proposed concentrated differential privacy) and can be used with existing differentially private mechanisms that train models using objective perturbation and output perturbation.more » « less
-
This paper surveys recent work in the intersection of differential privacy (DP) and fairness. It reviews the conditions under which privacy and fairness may have aligned or contrasting goals, analyzes how and why DP may exacerbate bias and unfairness in decision problems and learning tasks, and describes available mitigation measures for the fairness issues arising in DP systems. The survey provides a unified understanding of the main challenges and potential risks arising when deploying privacy-preserving machine-learning or decisions-making tasks under a fairness lens.more » « less
