We tackle the problem of group fairness in classification, where the objective is to learn
models that do not unjustly discriminate against subgroups of the population. Most existing …

Automated decision systems are increasingly used to make consequential decisions in
people's lives. Due to the sensitivity of the manipulated data and the resulting decisions …

In this article, we present a detailed review of current practices and state-of-the-art
methodologies in the field of differential privacy (DP), with a focus of advancing DP's …

Ensuring the trustworthiness of large language models (LLMs) is crucial. Most studies
concentrate on fully pre-trained LLMs to better understand and improve LLMs' …

Machine learning techniques are increasingly used for high-stakes decision-making, such
as college admissions, loan attribution or recidivism prediction. Thus, it is crucial to ensure …

Graph Neural Networks (GNNs) have emerged as a prominent graph learning model in
various graph-based tasks over the years. Nevertheless, due to the vulnerabilities of GNNs …

In this work, we investigate binary classification under the constraints of both differential
privacy and fairness. We first propose an algorithm based on the decoupling technique for …

Federated learning enables collaborative model training across multiple clients without
sharing raw data, adhering to privacy regulations, which involves clients sending model …

Automated decision systems are increasingly used to make consequential decisions in
people's lives. Due to the sensitivity of the manipulated data as well as the resulting …

Machine learning (ML) algorithms rely primarily on the availability of training data, and,
depending on the domain, these data may include sensitive information about the data …