Machine learning models are increasingly used in high-stakes decision-making systems. In such applications, a major concern is that these models sometimes discriminate against certain demographic groups such as individuals with certain race, gender, or age. Another major concern in these applications is the violation of the privacy of users. While fair learning algorithms have been developed to mitigate discrimination issues, these algorithms can still leak sensitive information, such as individuals’ health or financial records. Utilizing the notion of differential privacy (DP), prior works aimed at developing learning algorithms that are both private and fair. However, existing algorithms for DP fair learning are either not guaranteed to converge or require full batch of data in each iteration of the algorithm to converge. In this paper, we provide the first stochastic differentially private algorithm for fair learning that is guaranteed to converge. Here, the term “stochastic" refers to the fact that our proposed algorithm converges even when minibatches of data are used at each iteration (i.e. stochastic optimization). Our framework is flexible enough to permit different fairness notions, including demographic parity and equalized odds. In addition, our algorithm can be applied to non-binary classification tasks with multiple (non-binary) sensitive attributes. As a byproduct of our convergence analysis, we provide the first utility guarantee for a DP algorithm for solving nonconvex-strongly concave min-max problems. Our numerical experiments show that the proposed algorithm consistently offers significant performance gains over the state-of-the-art baselines, and can be applied to larger scale problems with non-binary target/sensitive attributes.
more »
« less
Constrained-Based Differential Privacy
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
- Award ID(s):
- 2133169
- NSF-PAR ID:
- 10337580
- Date Published:
- Journal Name:
- International Conference on Principles and Practice of Constraint Programming (CP 2021)
- Volume:
- 210
- ISSN:
- 1861-8960
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Organizations often collect private data and release aggregate statistics for the public’s benefit. If no steps toward preserving privacy are taken, adversaries may use released statistics to deduce unauthorized information about the individuals described in the private dataset. Differentially private algorithms address this challenge by slightly perturbing underlying statistics with noise, thereby mathematically limiting the amount of information that may be deduced from each data release. Properly calibrating these algorithms—and in turn the disclosure risk for people described in the dataset—requires a data curator to choose a value for a privacy budget parameter, ɛ . However, there is little formal guidance for choosing ɛ , a task that requires reasoning about the probabilistic privacy–utility tradeoff. Furthermore, choosing ɛ in the context of statistical inference requires reasoning about accuracy trade-offs in the presence of both measurement error and differential privacy (DP) noise. We present Vi sualizing P rivacy (ViP), an interactive interface that visualizes relationships between ɛ , accuracy, and disclosure risk to support setting and splitting ɛ among queries. As a user adjusts ɛ , ViP dynamically updates visualizations depicting expected accuracy and risk. ViP also has an inference setting, allowing a user to reason about the impact of DP noise on statistical inferences. Finally, we present results of a study where 16 research practitioners with little to no DP background completed a set of tasks related to setting ɛ using both ViP and a control. We find that ViP helps participants more correctly answer questions related to judging the probability of where a DP-noised release is likely to fall and comparing between DP-noised and non-private confidence intervals.more » « less
-
This paper introduces a differentially private (DP) mechanism to protect the information exchanged during the coordination of sequential and inter- dependent markets. This coordination represents a classic Stackelberg game and relies on the ex- change of sensitive information between the sys- tem agents. The paper is motivated by the observa- tion that the perturbation introduced by traditional DP mechanisms fundamentally changes the under- lying optimization problem and even leads to un- satisfiable instances. To remedy such limitation, the paper introduces the Privacy-Preserving Stack- elberg Mechanism (PPSM), a framework that en- forces the notions of feasibility and fidelity (i.e. near-optimality) of the privacy-preserving informa- tion to the original problem objective. PPSM com- plies with the notion of differential privacy and en- sures that the outcomes of the privacy-preserving coordination mechanism are close-to-optimality for each agent. Experimental results on several gas and electricity market benchmarks based on a real case study demonstrate the effectiveness of the proposed approach. A full version of this paper [Fioretto et al., 2020b] contains complete proofs and additional discussion on the motivating application.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
-
Post-processing immunity is a fundamental property of differential privacy: it enables arbitrary data-independent transformations to differentially private outputs without affecting their privacy guarantees. Post-processing is routinely applied in data-release applications, including census data, which are then used to make allocations with substantial societal impacts. This paper shows that post-processing causes disparate impacts on individuals or groups and analyzes two critical settings: the release of differentially private datasets and the use of such private datasets for downstream decisions, such as the allocation of funds informed by US Census data. In the first setting, the paper proposes tight bounds on the unfairness of traditional post-processing mechanisms, giving a unique tool to decision-makers to quantify the disparate impacts introduced by their release. In the second setting, this paper proposes a novel post-processing mechanism that is (approximately) optimal under different fairness metrics, either reducing fairness issues substantially or reducing the cost of privacy. The theoretical analysis is complemented with numerical simulations on Census data.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.4230/LIPIcs.CP.2021.2
