Related papers: The trade-off between data minimization and fairne…

Federated Reinforcement Learning (FRL) allows multiple agents to collaboratively build a decision making policy without sharing raw trajectories. However, if a small fraction of these agents are adversarial, it can lead to catastrophic…

This paper investigates the parameter space of machine learning (ML) algorithms in aggravating or mitigating fairness bugs. Data-driven software is increasingly applied in social-critical applications where ensuring fairness is of paramount…

Privacy and algorithmic fairness have become two central issues in modern machine learning. Although each has separately emerged as a rapidly growing research area, their joint effect remains comparatively under-explored. In this paper, we…

Deploying machine learning (ML) models often requires both fairness and privacy guarantees. Both of these objectives present unique trade-offs with the utility (e.g., accuracy) of the model. However, the mutual interactions between…

As machine learning (ML) systems increasingly shape access to credit, jobs, and other opportunities, the fairness of algorithmic decisions has become a central concern. Yet it remains unclear when enforcing fairness constraints in these…

Data minimization (DM) describes the principle of collecting only the data strictly necessary for a given task. It is a foundational principle across major data protection regulations like GDPR and CPRA. Violations of this principle have…

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…

The General Data Protection Regulation (GDPR) in the European Union is the most famous recently enacted privacy regulation. Despite of the regulation's legal, political, and technological ramifications, relatively little research has been…

Federated learning (FL) algorithms commonly aim to maximize clients' accuracy by training a model on their collective data. However, in several FL applications, the model's decisions should meet a group fairness constraint to be independent…

Explicit and implicit bias clouds human judgement, leading to discriminatory treatment of minority groups. A fundamental goal of algorithmic fairness is to avoid the pitfalls in human judgement by learning policies that improve the overall…

Federated learning enables training a global machine learning model from data distributed across multiple sites, without having to move the data. This is particularly relevant in healthcare applications, where data is rife with personal,…

Recommender Systems use the user's profile to generate a recommendation list with unknown items to a target user. Although the primary goal of traditional recommendation systems is to deliver the most relevant items, such an effort…

As reinforcement learning techniques are increasingly applied to real-world decision problems, attention has turned to how these algorithms use potentially sensitive information. We consider the task of training a policy that maximizes…

Recommender systems are one of the most pervasive applications of machine learning in industry, with many services using them to match users to products or information. As such it is important to ask: what are the possible fairness risks,…

Federated recommender systems enable collaborative model training while keeping user interaction data local and sharing only essential model parameters, thereby mitigating privacy risks. However, existing methods overlook a critical issue,…

The new General Data Protection Regulation (GDPR) will take effect in May 2018, and hence, designing compliant data protection policies and system architectures became crucial for organizations to avoid penalties. Unfortunately, the…

Following related work in law and policy, two notions of disparity have come to shape the study of fairness in algorithmic decision-making. Algorithms exhibit treatment disparity if they formally treat members of protected subgroups…

Addressing fairness concerns about machine learning models is a crucial step towards their long-term adoption in real-world automated systems. While many approaches have been developed for training fair models from data, little is known…

Generative models must ensure both privacy and fairness for Trustworthy AI. While these goals have been pursued separately, recent studies propose to combine existing privacy and fairness techniques to achieve both goals. However, naively…

The possible risk that AI systems could promote discrimination by reproducing and enforcing unwanted bias in data has been broadly discussed in research and society. Many current legal standards demand to remove sensitive attributes from…