Differentially Private and Fair Classification via Calibrated Functional Mechanism

Abstract

Machine learning is increasingly becoming a powerful tool to make decisions in a wide variety of applications, such as medical diagnosis and autonomous driving. Privacy concerns related to the training data and unfair behaviors of some decisions with regard to certain attributes (e.g., sex, race) are becoming more critical. Thus, constructing a fair machine learning model while simultaneously providing privacy protection becomes a challenging problem. In this paper, we focus on the design of classification model with fairness and differential privacy guarantees by jointly combining functional mechanism and decision boundary fairness. In order to enforce ϵ-differential privacy and fairness, we leverage the functional mechanism to add different amounts of Laplace noise regarding different attributes to the polynomial coefficients of the objective function in consideration of fairness constraint. We further propose an utility-enhancement scheme, called relaxed functional mechanism by adding Gaussian noise instead of Laplace noise, hence achieving (ϵ, δ)-differential privacy. Based on the relaxed functional mechanism, we can design (ϵ, δ)-differentially private and fair classification model. Moreover, our theoretical analysis and empirical results demonstrate that our two approaches achieve both fairness and differential privacy while preserving good utility and outperform the state-of-the-art algorithms.

Differentially Private Robust ADMM for Distributed Machine Learning

“…For the privacy-preserving data analysis, the standard privacy metric, Differential privacy (DP) [9,11], is proposed to measure the privacy risk of each data sample in the dataset, and has already been adopted in many machine learning domains [4,8,18,20,24]. Basically, under DP framework, privacy protection is guaranteed by limiting the difference of the distribution of the output regardless of the value change of any one sample in the dataset.…”

More Than Privacy: Applying Differential Privacy in Key Areas of Artificial Intelligence

“…Recently, researchers have attempted to adopt differential privacy to simultaneously achieve both fairness and privacy preservation [52], [53]. This research is motivated by settings where models are required to be non-discriminatory in terms of certain attributes, but these attributes may be sensitive and so must be protected while training the model [54].…”

“…This research is motivated by settings where models are required to be non-discriminatory in terms of certain attributes, but these attributes may be sensitive and so must be protected while training the model [54]. Addressing fairness and privacy preservation simultaneously is challenging because they have different aims [53], [55]. Fairness focuses on the group level and seeks to guarantee that the model's predictions for a protected group (such as female) are the same as the predictions made for an unprotected group.…”

“…Privacy preservation guarantees that the output of a classification model is independent of whether any individual record is in or out of the training dataset. A typical solution to achieve fairness and privacy preservation simultaneously was proposed by Ding et al [53]. Their solution is to add a different amount of differentially private noise based on different polynomial coefficients of the constrained objective function, where the coefficients relate to attributes in the training dataset.…”

Towards Plausible Differentially Private ADMM Based Distributed Machine Learning

“…For the privacy-preserving data analysis, the standard privacy metric, Dierential privacy (DP) [9,11], is proposed to measure the privacy risk of each data sample in the dataset, and has already been adopted in many machine learning domains [4,8,18,20,24]. Basically, under DP framework, privacy protection is guaranteed by limiting the dierence of the distribution of the output regardless of the value change of any one sample in the dataset.…”