Through the lens of information-theoretic reductions, we examine a reductions approach to fair optimization and learning where a black-box optimizer is used to learn a fair model for classification or regression. Quantifying the complexity, both statistically and computationally, of making such models satisfy the rigorous definition of differential privacy is our end goal. We resolve a few open questions and show applicability to fair machine learning, hypothesis testing, and to optimizing non-standard measures of classification loss. Furthermore, our sample complexity bounds are tight amongst all strategies that jointly minimize a composition of functions.
The reductions approach to fair optimization can be abstracted as the constrained group-objective optimization problem where we aim to optimize an objective that is a function of losses of individual groups, subject to some constraints. We give the first polynomial-time algorithms to solve the problem with $(ε, 0)$ or $(ε, δ)$ differential privacy guarantees when defined on a convex decision set (for example, the $\ell_P$ unit ball) with convex constraints and losses. Accompanying information-theoretic lower bounds for the problem are presented. In addition, compared to a previous method for ensuring differential privacy subject to a relaxed form of the equalized odds fairness constraint, the $(ε, δ)$-differentially private algorithm we present provides asymptotically better sample complexity guarantees, resulting in an exponential improvement in certain parameter regimes. We introduce a class of bounded divergence linear optimizers, which could be of independent interest, and specialize to pure and approximate differential privacy.
Differential Privacy (DP) is an important privacy-enhancing technology for private machine learning systems. It allows to measure and bound the risk associated with an individual participation in a computation. However, it was recently observed that DP learning systems may exacerbate bias and unfairness for different groups of individuals. This paper builds on these important observations and sheds light on the causes of the disparate impacts arising in the problem of differentially private empirical risk minimization. It focuses on the accuracy disparity arising among groups of individuals in…
Microsoft Research（微软研究院）；University of Minnesota（明尼苏达大学）
In this paper, we study the prediction of a real-valued target, such as a risk score or recidivism rate, while guaranteeing a quantitative notion of fairness with respect to a protected attribute such as gender or race. We call this class of problems \emph{fair regression}. We propose general schemes for fair regression under two notions of fairness: (1) statistical parity, which asks that the prediction be statistically independent of the protected attribute, and (2) bounded group loss, which asks that the prediction error restricted to any protected group remain below some pre-determined lev…
End users and regulators require private and fair artificial intelligence models, but previous work suggests these objectives may be at odds. We use the CivilComments to evaluate the impact of applying the {\em de facto} standard approach to privacy, DP-SGD, across several fairness metrics. We evaluate three implementations of DP-SGD: for dimensionality reduction (PCA), linear classification (logistic regression), and robust deep learning (Group-DRO). We establish a negative, logarithmic correlation between privacy and fairness in the case of linear classification and robust deep learning. DP-…
Princeton University（普林斯顿大学）；The Ohio State University（俄亥俄州立大学）；Google AI（谷歌人工智能）
We consider learning problems where the training set consists of two types of examples: private and public. The goal is to design a learning algorithm that satisfies differential privacy only with respect to the private examples. This setting interpolates between private learning (where all examples are private) and classical learning (where all examples are public). We study the limits of learning in this setting in terms of private and public sample complexities. We show that any hypothesis class of VC-dimension $d$ can be agnostically learned up to an excess error of $α$ using only (roughly…
National University of Singapore（新加坡国立大学）；The University of Melbourne（墨尔本大学）；IBM Singapore Lab（IBM新加坡实验室）；Monash University（莫纳什大学）；Deakin University（迪肯大学）
This paper firstly considers the research problem of fairness in collaborative deep learning, while ensuring privacy. A novel reputation system is proposed through digital tokens and local credibility to ensure fairness, in combination with differential privacy to guarantee privacy. In particular, we build a fair and differentially private decentralised deep learning framework called FDPDDL, which enables parties to derive more accurate local models in a fair and private manner by using our developed two-stage scheme: during the initialisation stage, artificial samples generated by Differentia…
National University of Singapore（新加坡国立大学）；Monash University（莫纳什大学）；The University of Melbourne（墨尔本大学）
It has been demonstrated that hidden representation learned by a deep model can encode private information of the input, hence can be exploited to recover such information with reasonable accuracy. To address this issue, we propose a novel approach called Differentially Private Neural Representation (DPNR) to preserve the privacy of the extracted representation from text. DPNR utilises Differential Privacy (DP) to provide a formal privacy guarantee. Further, we show that masking words via dropout can further enhance privacy. To maintain utility of the learned representation, we integrate DP-no…
Seldon（塞尔顿）；University of California San Diego（加州大学圣地亚哥分校）；Ford R&A（福特研发中心）；University of Oxford（牛津大学）；OpenMined（开放挖掘）
Deployment of deep learning in different fields and industries is growing day by day due to its performance, which relies on the availability of data and compute. Data is often crowd-sourced and contains sensitive information about its contributors, which leaks into models that are trained on it. To achieve rigorous privacy guarantees, differentially private training mechanisms are used. However, it has recently been shown that differential privacy can exacerbate existing biases in the data and have disparate impacts on the accuracy of different subgroups of data. In this paper, we aim to stud…
We show a generic reduction from multiclass differentially private PAC learning to binary private PAC learning. We apply this transformation to a recently proposed binary private PAC learner to obtain a private multiclass learner with sample complexity that has a polynomial dependence on the multiclass Littlestone dimension and a poly-logarithmic dependence on the number of classes. This yields an exponential improvement in the dependence on both parameters over learners from previous work. Our proof extends the notion of $Ψ$-dimension defined in work of Ben-David et al. [JCSS '95] to the onli…
Fair machine learning has become a significant research topic with broad societal impact. However, most fair learning methods require direct access to personal demographic data, which is increasingly restricted to use for protecting user privacy (e.g. by the EU General Data Protection Regulation). In this paper, we propose a distributed fair learning framework for protecting the privacy of demographic data. We assume this data is privately held by a third party, which can communicate with the data center (responsible for model development) without revealing the demographic information. We prop…
KTH Royal Institute of Technology（KTH皇家理工学院）；Apple（苹果公司）
Federated learning with differential privacy, or private federated learning, provides a strategy to train machine learning models while respecting users' privacy. However, differential privacy can disproportionately degrade the performance of the models on under-represented groups, as these parts of the distribution are difficult to learn in the presence of noise. Existing approaches for enforcing fairness in machine learning models have considered the centralized setting, in which the algorithm has access to the users' data. This paper introduces an algorithm to enforce group fairness in priv…
McMaster University（麦克马斯特大学）；Vector Institute（向量研究院）；Google（谷歌）；University of Toronto（多伦多大学）
We present a fairly general framework for reducing $(\varepsilon, δ)$ differentially private (DP) statistical estimation to its non-private counterpart. As the main application of this framework, we give a polynomial time and $(\varepsilon,δ)$-DP algorithm for learning (unrestricted) Gaussian distributions in $\mathbb{R}^d$. The sample complexity of our approach for learning the Gaussian up to total variation distance $α$ is $\widetilde{O}(d^2/α^2 + d^2\sqrt{\ln(1/δ)}/α\varepsilon + d\ln(1/δ) / α\varepsilon)$ matching (up to logarithmic factors) the best known information-theoretic (non-effici…
Vienna University of Technology（维也纳技术大学）；University of Alicante（阿利坎特大学）
As the privacy risks posed by camera surveillance and facial recognition have grown, so has the research into privacy preservation algorithms. Among these, visual privacy preservation algorithms attempt to impart bodily privacy to subjects in visuals by obfuscating privacy-sensitive areas. While disparate performances of facial recognition systems across phenotypes are the subject of much study, its counterpart, privacy preservation, is not commonly analysed from a fairness perspective. In this paper, the fairness of commonly used visual privacy preservation algorithms is investigated through …
University of Houston（休斯顿大学）；Guilin University of Electronic Technology（桂林电子科技大学）；Guangdong University of Technology（广东工业大学）
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 …
Syracuse University（雪城大学）；Georgia Institute of Technology（佐治亚理工学院）
A critical concern in data-driven decision making is to build models whose outcomes do not discriminate against some demographic groups, including gender, ethnicity, or age. To ensure non-discrimination in learning tasks, knowledge of the sensitive attributes is essential, while, in practice, these attributes may not be available due to legal and ethical requirements. To address this challenge, this paper studies a model that protects the privacy of the individuals sensitive information while also allowing it to learn non-discriminatory predictors. The method relies on the notion of differenti…
Massachusetts Institute of Technology（麻省理工学院）；University of Illinois at Chicago（伊利诺伊大学芝加哥分校）；Toyota Technological Institute at Chicago（芝加哥丰田工业大学）
Sensitive attributes such as race are rarely available to learners in real world settings as their collection is often restricted by laws and regulations. We give a scheme that allows individuals to release their sensitive information privately while still allowing any downstream entity to learn non-discriminatory predictors. We show how to adapt non-discriminatory learners to work with privatized protected attributes giving theoretical guarantees on performance. Finally, we highlight how the methodology could apply to learning fair predictors in settings where protected attributes are only av…
Etsy Inc（Etsy公司）；Rutgers University（罗格斯大学）；University at Albany, SUNY（纽约州立大学奥尔巴尼分校）
Recently, there has been an increasing adoption of differential privacy guided algorithms for privacy-preserving machine learning tasks. However, the use of such algorithms comes with trade-offs in terms of algorithmic fairness, which has been widely acknowledged. Specifically, we have empirically observed that the classical collaborative filtering method, trained by differentially private stochastic gradient descent (DP-SGD), results in a disparate impact on user groups with respect to different user engagement levels. This, in turn, causes the original unfair model to become even more biased…
The Private Aggregation of Teacher Ensembles (PATE) is an important private machine learning framework. It combines multiple learning models used as teachers for a student model that learns to predict an output chosen by noisy voting among the teachers. The resulting model satisfies differential privacy and has been shown effective in learning high-quality private models in semisupervised settings or when one wishes to protect the data labels. This paper asks whether this privacy-preserving framework introduces or exacerbates bias and unfairness and shows that PATE can introduce accuracy dispa…
Encoded text representations often capture sensitive attributes about individuals (e.g., race or gender), which raise privacy concerns and can make downstream models unfair to certain groups. In this work, we propose FEDERATE, an approach that combines ideas from differential privacy and adversarial training to learn private text representations which also induces fairer models. We empirically evaluate the trade-off between the privacy of the representations and the fairness and accuracy of the downstream model on four NLP datasets. Our results show that FEDERATE consistently improves upon pre…
Syracuse University（雪城大学）；Georgia Institute of Technology（佐治亚理工学院）
A critical concern in data-driven processes is to build models whose outcomes do not discriminate against some demographic groups, including gender, ethnicity, or age. To ensure non-discrimination in learning tasks, knowledge of the group attributes is essential. However, in practice, these attributes may not be available due to legal and ethical requirements. To address this challenge, this paper studies a model that protects the privacy of the individuals' sensitive information while also allowing it to learn non-discriminatory predictors. A key characteristic of the proposed model is to ena…
Northeastern University（东北大学）；University of Pennsylvania（宾夕法尼亚大学）
Motivated by settings in which predictive models may be required to be non-discriminatory with respect to certain attributes (such as race), but even collecting the sensitive attribute may be forbidden or restricted, we initiate the study of fair learning under the constraint of differential privacy. We design two learning algorithms that simultaneously promise differential privacy and equalized odds, a 'fairness' condition that corresponds to equalizing false positive and negative rates across protected groups. Our first algorithm is a private implementation of the equalized odds post-process…
FAIRPLAI: A Human-in-the-Loop Approach to Fair and Private Machine Learning
Dept. of Computer Science, The University of Texas at El Paso（得克萨斯大学埃尔帕索分校计算机科学系）；Dept. of Mathematics, Mountain View High School（山景高中数学系）；Dept. of Mathematics, El Paso Independent School District（埃尔帕索独立学区数学系）
We study the relationship between the notions of differentially private learning and online learning in games. Several recent works have shown that differentially private learning implies online learning, but an open problem of Neel, Roth, and Wu \cite{NeelAaronRoth2018} asks whether this implication is {\it efficient}. Specifically, does an efficient differentially private learner imply an efficient online learner? In this paper we resolve this open question in the context of pure differential privacy. We derive an efficient black-box reduction from differentially private learning to online l…
Private and Robust Contribution Evaluation in Federated Learning
University of La Laguna（拉拉加大学）；HUN-REN Hungarian Research Network（HUN-REN匈牙利研究网络）；Chalmers University（查尔姆斯大学）；Budapest University of Technology and Economics（布达佩斯技术经济大学）
The recent rise of privacy concerns has led researchers to devise methods for private neural inference -- where inferences are made directly on encrypted data, never seeing inputs. The primary challenge facing private inference is that computing on encrypted data levies an impractically-high latency penalty, stemming mostly from non-linear operators like ReLU. Enabling practical and private inference requires new optimization methods that minimize network ReLU counts while preserving accuracy. This paper proposes DeepReDuce: a set of optimizations for the judicious removal of ReLUs to reduce p…
Diferentially private (DP) synthetic datasets are a powerful approach for training machine learning models while respecting the privacy of individual data providers. The effect of DP on the fairness of the resulting trained models is not yet well understood. In this contribution, we systematically study the effects of differentially private synthetic data generation on classification. We analyze disparities in model utility and bias caused by the synthetic dataset, measured through algorithmic fairness metrics. Our first set of results show that although there seems to be a clear negative corr…
In this article, we propose a new variational approach to learn private and/or fair representations. This approach is based on the Lagrangians of a new formulation of the privacy and fairness optimization problems that we propose. In this formulation, we aim to generate representations of the data that keep a prescribed level of the relevant information that is not shared by the private or sensitive data, while minimizing the remaining information they keep. The proposed approach (i) exhibits the similarities of the privacy and fairness problems, (ii) allows us to control the trade-off between…
Security, privacy, and fairness have become critical in the era of data science and machine learning. More and more we see that achieving universally secure, private, and fair systems is practically impossible. We have seen for example how generative adversarial networks can be used to learn about the expected private training data; how the exploitation of additional data can reveal private information in the original one; and how what looks like unrelated features can teach us about each other. Confronted with this challenge, in this paper we open a new line of research, where the security, p…
Achieving Hilbert-Schmidt Independence Under Rényi Differential Privacy for Fair and Private Data Generation
Department of Mathematics and Computer Science University of Southern Denmark（丹麦南部大学数学与计算机科学系）；Department of Mathematics and Computer Science Freie Universität Berlin（柏林自由大学数学与计算机科学系）；Faculty for Informatik Universität der Bundeswehr München（联邦国防军大学慕尼黑信息学院）
Reliable neural networks (NNs) provide important inference-time reliability guarantees such as fairness and robustness. Complementarily, privacy-preserving NN inference protects the privacy of client data. So far these two emerging areas have been largely disconnected, yet their combination will be increasingly important. In this work, we present the first system which enables privacy-preserving inference on reliable NNs. Our key idea is to design efficient fully homomorphic encryption (FHE) counterparts for the core algorithmic building blocks of randomized smoothing, a state-of-the-art techn…
Australian National University（澳大利亚国立大学）；Monash University（莫纳什大学）
Federated learning (FL) allows predictive model training on the sensed data in a wireless Internet of things (IoT) network evading data collection cost in terms of energy, time, and privacy. In this paper, for a FL setting, we model the learning gain achieved by an IoT device against its participation cost as its utility. The local model quality and the associated cost differs from device to device due to the device-heterogeneity which could be time-varying. We identify that this results in utility unfairness because the same global model is shared among the devices. In the vanilla FL setting,…
We present a systematic approach for achieving fairness in a binary classification setting. While we focus on two well-known quantitative definitions of fairness, our approach encompasses many other previously studied definitions as special cases. The key idea is to reduce fair classification to a sequence of cost-sensitive classification problems, whose solutions yield a randomized classifier with the lowest (empirical) error subject to the desired constraints. We introduce two reductions that work for any representation of the cost-sensitive classifier and compare favorably to prior baseline…
