Related papers: Fairness Issues and Mitigations in (Differentially…
The increasing use of machine learning in sensitive applications demands algorithms that simultaneously preserve data privacy and ensure fairness across potentially sensitive sub-populations. While privacy and fairness have each been…
Recommender systems are essential for personalizing digital experiences on e-commerce sites, streaming services, and social media platforms. While these systems are necessary for modern digital interactions, they face fairness, bias,…
Supervised learning models have been increasingly used for making decisions about individuals in applications such as hiring, lending, and college admission. These models may inherit pre-existing biases from training datasets and…
Differential Privacy (DP) is the current gold-standard for ensuring privacy for statistical queries. Estimation problems under DP constraints appearing in the literature have largely focused on providing equal privacy to all users. We…
Privacy-preserving data analysis is a rising challenge in contemporary statistics, as the privacy guarantees of statistical methods are often achieved at the expense of accuracy. In this paper, we investigate the tradeoff between…
There are now several large scale deployments of differential privacy used to collect statistical information about users. However, these deployments periodically recollect the data and recompute the statistics using algorithms designed for…
Statistical heterogeneity is a measure of how skewed the samples of a dataset are. It is a common problem in the study of differential privacy that the usage of a statistically heterogeneous dataset results in a significant loss of…
Conducting disparity assessments at regular time intervals is critical for surfacing potential biases in decision-making and improving outcomes across demographic groups. Because disparity assessments fundamentally depend on the…
Accurately measuring discrimination is crucial to faithfully assessing fairness of trained machine learning (ML) models. Any bias in measuring discrimination leads to either amplification or underestimation of the existing disparity.…
Mitigating the disparate impact of statistical machine learning methods is crucial for ensuring fairness. While extensive research aims to reduce disparity, the effect of using a \emph{finite dataset} -- as opposed to the entire population…
The authors discuss their experience applying differential privacy with a complex data set with the goal of enabling standard approaches to statistical data analysis. They highlight lessons learned and roadblocks encountered, distilling…
How to properly set the privacy parameter in differential privacy (DP) has been an open question in DP research since it was first proposed in 2006. In this work, we demonstrate the ability of influence functions to offer insight into how a…
Auditing differential privacy has emerged as an important area of research that supports the design of privacy-preserving mechanisms. Privacy audits help to obtain empirical estimates of the privacy parameter, to expose flawed…
The increasing impact of algorithmic decisions on people's lives compels us to scrutinize their fairness and, in particular, the disparate impacts that ostensibly-color-blind algorithms can have on different groups. Examples include credit…
Differentially private data generation techniques have become a promising solution to the data privacy challenge -- it enables sharing of data while complying with rigorous privacy guarantees, which is essential for scientific progress in…
Recent years, local differential privacy (LDP) has been adopted by many web service providers like Google \cite{erlingsson2014rappor}, Apple \cite{apple2017privacy} and Microsoft \cite{bolin2017telemetry} to collect and analyse users' data…
Normalizing flow models have risen as a popular solution to the problem of density estimation, enabling high-quality synthetic data generation as well as exact probability density evaluation. However, in contexts where individuals are…
Estimating causal effects from randomized experiments is only possible if participants are willing to disclose their potentially sensitive responses. Differential privacy, a widely used framework for ensuring an algorithms privacy…
To better understand discriminations and the effect of affirmative actions in selection problems (e.g., college admission or hiring), a recent line of research proposed a model based on differential variance. This model assumes that the…
Popular approaches to differential privacy, such as the Laplace and exponential mechanisms, calibrate randomised smoothing through global sensitivity of the target non-private function. Bounding such sensitivity is often a prohibitively…