Pedro Henriques Abreu

Abstract
Group fairness in machine learning is an important area of research focused on achieving equitable outcomes across different groups defined by sensitive attributes such as race or gender. Federated learning, a decentralized approach to training machine learning models across multiple clients, amplifies the need for fairness methodologies due to its inherent heterogeneous data distributions that can exacerbate biases. The intersection of federated learning and group fairness has attracted significant interest, with 48 research works specifically dedicated to addressing this issue. However, no comprehensive survey has specifically focused on group fairness in Federated Learning. In this work, we analyze the key challenges of this topic, propose practices for its identification and benchmarking, and create a novel taxonomy based on criteria such as data partitioning, location, and strategy. Furthermore, we analyze broader concerns, review how different approaches handle the complexities of various sensitive attributes, examine common datasets and applications, and discuss the ethical, legal, and policy implications of group fairness in FL. We conclude by highlighting key areas for future research, emphasizing the need for more methods to address the complexities of achieving group fairness in federated systems.

Abstract
In the evolving field of machine learning, ensuring group fairness has become a critical concern, prompting the development of algorithms designed to mitigate bias in decision-making processes. Group fairness refers to the principle that a model's decisions should be equitable across different groups defined by sensitive attributes such as gender or race, ensuring that individuals from privileged groups and unprivileged groups are treated fairly and receive similar outcomes. However, achieving fairness in the presence of group-specific concept drift remains an unexplored frontier, and our research represents pioneering efforts in this regard. Group-specific concept drift refers to situations where one group experiences concept drift over time, while another does not, leading to a decrease in fairness even if accuracy (ACC) remains fairly stable. Within the framework of federated learning (FL), where clients collaboratively train models, its distributed nature further amplifies these challenges since each client can experience group-specific concept drift independently while still sharing the same underlying concept, creating a complex and dynamic environment for maintaining fairness. The most significant contribution of our research is the formalization and introduction of the problem of group-specific concept drift and its distributed counterpart, shedding light on its critical importance in the field of fairness. In addition, leveraging insights from prior research, we adapt an existing distributed concept drift adaptation algorithm to tackle group-specific distributed concept drift, which uses a multimodel approach, a local group-specific drift detection mechanism, and continuous clustering of models over time. The findings from our experiments highlight the importance of addressing group-specific concept drift and its distributed counterpart to advance fairness in machine learning.

Abstract
Cybersecurity attacks, such as poisoning and evasion, can intentionally introduce false or misleading information in different forms into data, potentially leading to catastrophic consequences for critical infrastructures, like water supply or energy power plants. While numerous studies have investigated the impact of these attacks on model-based prediction approaches, they often overlook the impurities present in the data used to train these models. One of those forms is missing data, the absence of values in one or more features. This issue is typically addressed by imputing missing values with plausible estimates, which directly impacts the performance of the classifier. The goal of this work is to promote a Data-centric AI approach by investigating how different types of cybersecurity attacks impact the imputation process. To this end, we conducted experiments using four popular evasion and poisoning attacks strategies across 29 real-world datasets, including the NSL-KDD and Edge-IIoT datasets, which were used as case study. For the adversarial attack strategies, we employed the Fast Gradient Sign Method, Carlini & Wagner, Project Gradient Descent, and Poison Attack against Support Vector Machine algorithm. Also, four state-of-the-art imputation strategies were tested under Missing Not At Random, Missing Completely at Random, and Missing At Random mechanisms using three missing rates (5%, 20%, 40%). We assessed imputation quality using MAE, while data distribution shifts were analyzed with the Kolmogorov-Smirnov and Chi-square tests. Furthermore, we measured classification performance by training an XGBoost classifier on the imputed datasets, using F1-score, Accuracy, and AUC. To deepen our analysis, we also incorporated six complexity metrics to characterize how adversarial attacks and imputation strategies impact dataset complexity. Our findings demonstrate that adversarial attacks significantly impact the imputation process. In terms of imputation assessment in what concerns to quality error, the scenario that enrolees imputation with Project Gradient Descent attack proved to be more robust in comparison to other adversarial methods. Regarding data distribution error, results from the Kolmogorov-Smirnov test indicate that in the context of numerical features, all imputation strategies differ from the baseline (without missing data) however for the categorical context Chi-Squared test proved no difference between imputation and the baseline.

Abstract
Quasi-identifiers (QIDs) are attributes in a dataset that are not directly unique identifiers of the users/entities themselves but can be used, often in conjunction with other datasets or information, to identify individuals and thus present a privacy risk in data sharing and analysis. Identifying QIDs is important in developing proper strategies for anonymization and data sanitization. This paper proposes QIDLEARNINGLIB, a Python library that offers a set of metrics and tools to measure the qualities of QIDs and identify them in data sets. It incorporates metrics from different domains-causality, privacy, data utility, and performance-to offer a holistic assessment of the properties of attributes in a given tabular dataset. Furthermore, QIDLEARNINGLIB offers visual analysis tools to present how these metrics shift over a dataset and implements an extensible framework that employs multiple optimization algorithms such as an evolutionary algorithm, simulated annealing, and greedy search using these metrics to identify a meaningful set of QIDs.

Abstract
Capsule endoscopy has emerged as a non-invasive alternative to traditional gastrointestinal inspection procedures, such as endoscopy and colonoscopy. Removing sedation risks, it is a patient-friendly and hospital-free procedure, which allows small bowel assessment, region not easily accessible by traditional methods. Recently, deep learning techniques have been employed to analyse capsule endoscopy images, with a focus on lesion classification and/or capsule location along the gastrointestinal tract. This research work presents a novel approach for testing the generalization capacity of deep learning techniques in the lesion location identification process using capsule endoscopy images. To achieve that, AlexNet, InceptionV3 and ResNet-152 architectures were trained exclusively in normal frames and later tested in lesion frames. Frames were sourced from KID and Kvasir-Capsule open-source datasets. Both RGB and grayscale representations were evaluated, and experiments with complete images and patches were made. Results show that the generalization capacity on lesion location of models is not so strong as their capacity for normal frame location, with colon being the most difficult organ to identify.