Based on data, machine learning can quickly and efficiently analyze large amounts of information to provide suggestions and help make decisions. For example, phones and computers expose us to machine learning technologies such as voice recognition, personalized shopping suggestions, targeted advertisements and email filtering. However, it also brings challenges related to bias in the data and algorithms it uses, potentially leading to discrimination against specific individuals or groups. To help combat this problem, Dr Na Zou, an assistant professor in the Department of Engineering Technology and Industrial Distribution at Texas A&M University, aims to develop a data-centric fairness framework. To support her research, Zou received the National Science Foundation's Faculty Early Career Development Program (CAREER) Award.

The definition and implementation of fairness in automated decisions has been extensively studied by the research community. Yet, there hides fallacious reasoning, misleading assertions, and questionable practices at the foundations of the current fair machine learning paradigm. Those flaws are the result of a failure to understand that the trade-off between statistically accurate outcomes and group similar outcomes exists as independent, external constraint rather than as a subjective manifestation as has been commonly argued. First, we explain that there is only one conception of fairness present in the fair machine learning literature: group similarity of outcomes based on a sensitive attribute where the similarity benefits an underprivileged group. Second, we show that there is, in fact, a trade-off between statistically accurate outcomes and group similar outcomes in any data setting where group disparities exist, and that the trade-off presents an existential threat to the equitable, fair machine learning approach. Third, we introduce a proof-of-concept evaluation to aid researchers and designers in understanding the relationship between statistically accurate outcomes and group similar outcomes. Finally, suggestions for future work aimed at data scientists, legal scholars, and data ethicists that utilize the conceptual and experimental framework described throughout this article are provided.

Over the past several years, a slew of different methods to measure the fairness of a machine learning model have been proposed. However, despite the growing number of publications and implementations, there is still a critical lack of literature that explains the interplay of fair machine learning with the social sciences of philosophy, sociology, and law. We hope to remedy this issue by accumulating and expounding upon the thoughts and discussions of fair machine learning produced by both social and formal (specifically machine learning and statistics) sciences in this field guide. Specifically, in addition to giving the mathematical and algorithmic backgrounds of several popular statistical and causal-based fair machine learning methods, we explain the underlying philosophical and legal thoughts that support them. Further, we explore several criticisms of the current approaches to fair machine learning from sociological and philosophical viewpoints. It is our hope that this field guide will help fair machine learning practitioners better understand how their algorithms align with important humanistic values (such as fairness) and how we can, as a field, design methods and metrics to better serve oppressed and marginalized populaces.

Algorithmic fairness has attracted significant attention in recent years, with many quantitative measures suggested for characterizing the fairness of different machine learning algorithms. Despite this interest, the robustness of those fairness measures with respect to an intentional adversarial attack has not been properly addressed. Indeed, most adversarial machine learning has focused on the impact of malicious attacks on the accuracy of the system, without any regard to the system's fairness. We propose new types of data poisoning attacks where an adversary intentionally targets the fairness of a system. Specifically, we propose two families of attacks that target fairness measures. In the anchoring attack, we skew the decision boundary by placing poisoned points near specific target points to bias the outcome. In the influence attack on fairness, we aim to maximize the covariance between the sensitive attributes and the decision outcome and affect the fairness of the model. We conduct extensive experiments that indicate the effectiveness of our proposed attacks.

We've visited the topic of fairness in the context of machine learning several times on The Morning Paper (see e.g. I'm still picking up new insights every time I revisit the topic though, and today's paper choice is no exception. In 1911 Russell & Whitehead published Principia Mathematica, with the goal of providing a solid foundation for all of mathematics. In 1931 Gödel's Incompleteness Theorem shattered the dream, showing that for any consistent axiomatic system there will always be theorems that cannot be proven within the system. In case you're wondering where on earth I'm going with this… it's a very stretched analogy I've been playing with in my mind.

Inspired by recent breakthroughs in predictive modeling, practitioners in both industry and government have turned to machine learning with hopes of operationalizing predictions to drive automated decisions. Unfortunately, many social desiderata concerning consequential decisions, such as justice or fairness, have no natural formulation within a purely predictive framework. In efforts to mitigate these problems, researchers have proposed a variety of metrics for quantifying deviations from various statistical parities that we might expect to observe in a fair world and offered a variety of algorithms in attempts to satisfy subsets of these parities or to trade off the degree to which they are satisfied against utility. In this paper, we connect this approach to \emph{fair machine learning} to the literature on ideal and non-ideal methodological approaches in political philosophy. The ideal approach requires positing the principles according to which a just world would operate. In the most straightforward application of ideal theory, one supports a proposed policy by arguing that it closes a discrepancy between the real and the perfectly just world. However, by failing to account for the mechanisms by which our non-ideal world arose, the responsibilities of various decision-makers, and the impacts of proposed policies, naive applications of ideal thinking can lead to misguided interventions. In this paper, we demonstrate a connection between the fair machine learning literature and the ideal approach in political philosophy, and argue that the increasingly apparent shortcomings of proposed fair machine learning algorithms reflect broader troubles faced by the ideal approach. We conclude with a critical discussion of the harms of misguided solutions, a reinterpretation of impossibility results, and directions for future research.