María Victoria Luzón
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
María Victoria Luzón has a total of 50 co-authors. Here are the top co-authors by number of shared publications:
- Nuria Rodríguez-Barroso
Department of Computer Science and Artificial Intelligence Andalusian Research Institute in Data Science and Computational Intelligence (DaSCI) University of Granada Spain
15 shared publications - Francisco Herrera
University of Granada
14 shared publications - Eugenio Martínez-Cámara
Andalusian Research Institute in Data Science and Computational Intelligence University of Granada Spain
6 shared publications - Daniel Jiménez-López
Department of Computer Science and Artificial Intelligence Andalusian Research Institute in Data Science and Computational Intelligence (DaSCI) University of Granada Spain
5 shared publications Francisco Herrera
3 shared publications- Alberto Argente-Garrido
Andalusian Research Institute in Data Science and Computational Intelligence (DaSCI), University of Granada,Department of Computer Science and Artificial Intelligence,Granada,Spain,18071
2 shared publications
Latest Publications
- Open Access
- 14 February 2026
- Published by Elsevier in Information Fusion
- Vol. 132
From privacy to trust in the agentic era: a taxonomy of challenges in trustworthy federated learning through the lens of trust report 2.0
- 14 February 2026
- Published by Elsevier in Information Fusion
- Vol. 132
Open AccessFrom privacy to trust in the agentic era: a taxonomy of challenges in trustworthy federated learning through the lens of trust report 2.0
- Open Access
- 2 February 2026
- Published by Springer Nature in Machine Intelligence Research
- Vol. 23 (1) , 133-146
RAB2-DEF: Dynamic and Explainable Defense Against Adversarial Attacks in Federated Learning to Fair Poor Clients
When artificial intelligence is becoming popular, the concern and the need for regulation are growing, besides other requirements of the data privacy. In this context, federated learning is proposed as a solution to data privacy concerns derived from different source data scenarios due to its distributed learning. The defense mechanisms proposed in the literature focus only on defending against adversarial attacks and maintaining performance, ignoring other important qualities such as explainability and fairness to poor quality clients, dynamism in terms of attack configuration and generality in terms of being resilient against different kinds of attacks. In this work, we propose RAB 2 -DEF, a resilient defense against byzantine and backdoor attacks which is dynamic, explainable and fair to poor clients via local linear explanations. We test the performance of RAB 2 -DEF on image datasets and defending against the byzantine and backdoor attacks considering the state-of-the-art defenses, and the result reveals that RAB 2 -DEF is a proper defense while also enhancing the other qualities toward trustworthy artificial intelligence.
- 2 February 2026
- Published by Springer Nature in Machine Intelligence Research
- Vol. 23 (1) , 133-146
Open AccessRAB2-DEF: Dynamic and Explainable Defense Against Adversarial Attacks in Federated Learning to Fair Poor Clients
When artificial intelligence is becoming popular, the concern and the need for regulation are growing, besides other requirements of the data privacy. In this context, federated learning is proposed as a solution to data privacy concerns derived from different source data scenarios due to its distributed learning. The defense mechanisms proposed in the literature focus only on defending against adversarial attacks and maintaining performance, ignoring other important qualities such as explainability and fairness to poor quality clients, dynamism in terms of attack configuration and generality in terms of being resilient against different kinds of attacks. In this work, we propose RAB 2 -DEF, a resilient defense against byzantine and backdoor attacks which is dynamic, explainable and fair to poor clients via local linear explanations. We test the performance of RAB 2 -DEF on image datasets and defending against the byzantine and backdoor attacks considering the state-of-the-art defenses, and the result reveals that RAB 2 -DEF is a proper defense while also enhancing the other qualities toward trustworthy artificial intelligence.
- Open Access
- 16 September 2025
- Published by Elsevier in Future Generation Computer Systems
- Vol. 176
Addressing data quality decompensation in federated learning via dynamic client selection
- 16 September 2025
- Published by Elsevier in Future Generation Computer Systems
- Vol. 176
Open AccessAddressing data quality decompensation in federated learning via dynamic client selection
- Open Access
Addressing Data Quality Decompensation in Federated Learning via Dynamic Client Selection
In cross-silo Federated Learning (FL), client selection is critical to ensure high model performance, yet it remains challenging due to data quality decompensation, budget constraints, and incentive compatibility. As training progresses, these factors exacerbate client heterogeneity and degrade global performance. Most existing approaches treat these challenges in isolation, making jointly optimizing multiple factors difficult. To address this, we propose Shapley-Bid Reputation Optimized Federated Learning (SBRO-FL), a unified framework integrating dynamic bidding, reputation modeling, and cost-aware selection. Clients submit bids based on their perceived data quality, and their contributions are evaluated using Shapley values to quantify their marginal impact on the global model. A reputation system, inspired by prospect theory, captures historical performance while penalizing inconsistency. The client selection problem is formulated as a 0-1 integer program that maximizes reputation-weighted utility under budget constraints. Experiments on FashionMNIST, EMNIST, CIFAR-10, and SVHN datasets show that SBRO-FL improves accuracy, convergence speed, and robustness, even in adversarial and low-bid interference scenarios. Our results highlight the importance of balancing data reliability, incentive compatibility, and cost efficiency to enable scalable and trustworthy FL deployments.
Open AccessAddressing Data Quality Decompensation in Federated Learning via Dynamic Client Selection
In cross-silo Federated Learning (FL), client selection is critical to ensure high model performance, yet it remains challenging due to data quality decompensation, budget constraints, and incentive compatibility. As training progresses, these factors exacerbate client heterogeneity and degrade global performance. Most existing approaches treat these challenges in isolation, making jointly optimizing multiple factors difficult. To address this, we propose Shapley-Bid Reputation Optimized Federated Learning (SBRO-FL), a unified framework integrating dynamic bidding, reputation modeling, and cost-aware selection. Clients submit bids based on their perceived data quality, and their contributions are evaluated using Shapley values to quantify their marginal impact on the global model. A reputation system, inspired by prospect theory, captures historical performance while penalizing inconsistency. The client selection problem is formulated as a 0-1 integer program that maximizes reputation-weighted utility under budget constraints. Experiments on FashionMNIST, EMNIST, CIFAR-10, and SVHN datasets show that SBRO-FL improves accuracy, convergence speed, and robustness, even in adversarial and low-bid interference scenarios. Our results highlight the importance of balancing data reliability, incentive compatibility, and cost efficiency to enable scalable and trustworthy FL deployments.
- Open Access
- 20 May 2025
- Published by MDPI AG in Machine Learning and Knowledge Extraction
- Vol. 7 (2) , 43
Membership Inference Attacks Fueled by Few-Shot Learning to Detect Privacy Leakage and Address Data Integrity
Deep learning models have an intrinsic privacy issue as they memorize parts of their training data, creating a privacy leakage. Membership inference attacks (MIAs) exploit this to obtain confidential information about the data used for training, aiming to steal information. They can be repurposed as a measurement of data integrity by inferring whether the data were used to train a machine learning model. While state-of-the-art attacks achieve significant privacy leakage, their requirements render them infeasible, hindering their use as practical tools to assess the magnitude of the privacy risk. Moreover, the most appropriate evaluation metric of MIA, the true positive rate at a low false positive rate, lacks interpretability. We claim that the incorporation of few-shot learning techniques into the MIA field and a suitable qualitative and quantitative privacy evaluation measure should resolve these issues. In this context, our proposal is twofold. We propose a few-shot learning-based MIA, termed the FeS-MIA model, which eases the evaluation of the privacy breach of a deep learning model by significantly reducing the number of resources required for this purpose. Furthermore, we propose an interpretable quantitative and qualitative measure of privacy, referred to as the Log-MIA measure. Jointly, these proposals provide new tools to assess privacy leakages and to ease the evaluation of the training data integrity of deep learning models, i.e., to analyze the privacy breach of a deep learning model. Experiments carried out with MIA over image classification and language modeling tasks, and a comparison to the state of the art, show that our proposals excel in identifying privacy leakages in a deep learning model with little extra information.
- 20 May 2025
- Published by MDPI AG in Machine Learning and Knowledge Extraction
- Vol. 7 (2) , 43
Open AccessMembership Inference Attacks Fueled by Few-Shot Learning to Detect Privacy Leakage and Address Data Integrity
Deep learning models have an intrinsic privacy issue as they memorize parts of their training data, creating a privacy leakage. Membership inference attacks (MIAs) exploit this to obtain confidential information about the data used for training, aiming to steal information. They can be repurposed as a measurement of data integrity by inferring whether the data were used to train a machine learning model. While state-of-the-art attacks achieve significant privacy leakage, their requirements render them infeasible, hindering their use as practical tools to assess the magnitude of the privacy risk. Moreover, the most appropriate evaluation metric of MIA, the true positive rate at a low false positive rate, lacks interpretability. We claim that the incorporation of few-shot learning techniques into the MIA field and a suitable qualitative and quantitative privacy evaluation measure should resolve these issues. In this context, our proposal is twofold. We propose a few-shot learning-based MIA, termed the FeS-MIA model, which eases the evaluation of the privacy breach of a deep learning model by significantly reducing the number of resources required for this purpose. Furthermore, we propose an interpretable quantitative and qualitative measure of privacy, referred to as the Log-MIA measure. Jointly, these proposals provide new tools to assess privacy leakages and to ease the evaluation of the training data integrity of deep learning models, i.e., to analyze the privacy breach of a deep learning model. Experiments carried out with MIA over image classification and language modeling tasks, and a comparison to the state of the art, show that our proposals excel in identifying privacy leakages in a deep learning model with little extra information.
- Open Access
Improving $(α, f)$-Byzantine Resilience in Federated Learning via layerwise aggregation and cosine distance
The rapid development of artificial intelligence systems has amplified societal concerns regarding their usage, necessitating regulatory frameworks that encompass data privacy. Federated Learning (FL) is posed as potential solution to data privacy challenges in distributed machine learning by enabling collaborative model training {without data sharing}. However, FL systems remain vulnerable to Byzantine attacks, where malicious nodes contribute corrupted model updates. While Byzantine Resilient operators have emerged as a widely adopted robust aggregation algorithm to mitigate these attacks, its efficacy diminishes significantly in high-dimensional parameter spaces, sometimes leading to poor performing models. This paper introduces Layerwise Cosine Aggregation, a novel aggregation scheme designed to enhance robustness of these rules in such high-dimensional settings while preserving computational efficiency. A theoretical analysis is presented, demonstrating the superior robustness of the proposed Layerwise Cosine Aggregation compared to original robust aggregation operators. Empirical evaluation across diverse image classification datasets, under varying data distributions and Byzantine attack scenarios, consistently demonstrates the improved performance of Layerwise Cosine Aggregation, achieving up to a 16% increase in model accuracy.
Open AccessImproving $(α, f)$-Byzantine Resilience in Federated Learning via layerwise aggregation and cosine distance
The rapid development of artificial intelligence systems has amplified societal concerns regarding their usage, necessitating regulatory frameworks that encompass data privacy. Federated Learning (FL) is posed as potential solution to data privacy challenges in distributed machine learning by enabling collaborative model training {without data sharing}. However, FL systems remain vulnerable to Byzantine attacks, where malicious nodes contribute corrupted model updates. While Byzantine Resilient operators have emerged as a widely adopted robust aggregation algorithm to mitigate these attacks, its efficacy diminishes significantly in high-dimensional parameter spaces, sometimes leading to poor performing models. This paper introduces Layerwise Cosine Aggregation, a novel aggregation scheme designed to enhance robustness of these rules in such high-dimensional settings while preserving computational efficiency. A theoretical analysis is presented, demonstrating the superior robustness of the proposed Layerwise Cosine Aggregation compared to original robust aggregation operators. Empirical evaluation across diverse image classification datasets, under varying data distributions and Byzantine attack scenarios, consistently demonstrates the improved performance of Layerwise Cosine Aggregation, achieving up to a 16% increase in model accuracy.
- Open Access
Membership Inference Attacks fueled by Few-Short Learning to detect privacy leakage tackling data integrity
Deep learning models have an intrinsic privacy issue as they memorize parts of their training data, creating a privacy leakage. Membership Inference Attacks (MIA) exploit it to obtain confidential information about the data used for training, aiming to steal information. They can be repurposed as a measurement of data integrity by inferring whether it was used to train a machine learning model. While state-of-the-art attacks achieve a significant privacy leakage, their requirements are not feasible enough, hindering their role as practical tools to assess the magnitude of the privacy risk. Moreover, the most appropriate evaluation metric of MIA, the True Positive Rate at low False Positive Rate lacks interpretability. We claim that the incorporation of Few-Shot Learning techniques to the MIA field and a proper qualitative and quantitative privacy evaluation measure should deal with these issues. In this context, our proposal is twofold. We propose a Few-Shot learning based MIA, coined as the FeS-MIA model, which eases the evaluation of the privacy breach of a deep learning model by significantly reducing the number of resources required for the purpose. Furthermore, we propose an interpretable quantitative and qualitative measure of privacy, referred to as Log-MIA measure. Jointly, these proposals provide new tools to assess the privacy leakage and to ease the evaluation of the training data integrity of deep learning models, that is, to analyze the privacy breach of a deep learning model. Experiments carried out with MIA over image classification and language modeling tasks and its comparison to the state-of-the-art show that our proposals excel at reporting the privacy leakage of a deep learning model with little extra information.
Open AccessMembership Inference Attacks fueled by Few-Short Learning to detect privacy leakage tackling data integrity
Deep learning models have an intrinsic privacy issue as they memorize parts of their training data, creating a privacy leakage. Membership Inference Attacks (MIA) exploit it to obtain confidential information about the data used for training, aiming to steal information. They can be repurposed as a measurement of data integrity by inferring whether it was used to train a machine learning model. While state-of-the-art attacks achieve a significant privacy leakage, their requirements are not feasible enough, hindering their role as practical tools to assess the magnitude of the privacy risk. Moreover, the most appropriate evaluation metric of MIA, the True Positive Rate at low False Positive Rate lacks interpretability. We claim that the incorporation of Few-Shot Learning techniques to the MIA field and a proper qualitative and quantitative privacy evaluation measure should deal with these issues. In this context, our proposal is twofold. We propose a Few-Shot learning based MIA, coined as the FeS-MIA model, which eases the evaluation of the privacy breach of a deep learning model by significantly reducing the number of resources required for the purpose. Furthermore, we propose an interpretable quantitative and qualitative measure of privacy, referred to as Log-MIA measure. Jointly, these proposals provide new tools to assess the privacy leakage and to ease the evaluation of the training data integrity of deep learning models, that is, to analyze the privacy breach of a deep learning model. Experiments carried out with MIA over image classification and language modeling tasks and its comparison to the state-of-the-art show that our proposals excel at reporting the privacy leakage of a deep learning model with little extra information.
- Open Access
Krum Federated Chain (KFC): Using blockchain to defend against adversarial attacks in Federated Learning
Federated Learning presents a nascent approach to machine learning, enabling collaborative model training across decentralized devices while safeguarding data privacy. However, its distributed nature renders it susceptible to adversarial attacks. Integrating blockchain technology with Federated Learning offers a promising avenue to enhance security and integrity. In this paper, we tackle the potential of blockchain in defending Federated Learning against adversarial attacks. First, we test Proof of Federated Learning, a well known consensus mechanism designed ad-hoc to federated contexts, as a defense mechanism demonstrating its efficacy against Byzantine and backdoor attacks when at least one miner remains uncompromised. Second, we propose Krum Federated Chain, a novel defense strategy combining Krum and Proof of Federated Learning, valid to defend against any configuration of Byzantine or backdoor attacks, even when all miners are compromised. Our experiments conducted on image classification datasets validate the effectiveness of our proposed approaches.
Open AccessKrum Federated Chain (KFC): Using blockchain to defend against adversarial attacks in Federated Learning
Federated Learning presents a nascent approach to machine learning, enabling collaborative model training across decentralized devices while safeguarding data privacy. However, its distributed nature renders it susceptible to adversarial attacks. Integrating blockchain technology with Federated Learning offers a promising avenue to enhance security and integrity. In this paper, we tackle the potential of blockchain in defending Federated Learning against adversarial attacks. First, we test Proof of Federated Learning, a well known consensus mechanism designed ad-hoc to federated contexts, as a defense mechanism demonstrating its efficacy against Byzantine and backdoor attacks when at least one miner remains uncompromised. Second, we propose Krum Federated Chain, a novel defense strategy combining Krum and Proof of Federated Learning, valid to defend against any configuration of Byzantine or backdoor attacks, even when all miners are compromised. Our experiments conducted on image classification datasets validate the effectiveness of our proposed approaches.
- 20 December 2024
- Published by Elsevier in Information Fusion
- Vol. 117
FLEX: Flexible Federated Learning Framework
- 20 December 2024
- Published by Elsevier in Information Fusion
- Vol. 117
FLEX: Flexible Federated Learning Framework
- 28 November 2024
- Published by Elsevier in Information Sciences
- Vol. 694
An interpretable client decision tree aggregation process for federated learning
- 28 November 2024
- Published by Elsevier in Information Sciences
- Vol. 694
An interpretable client decision tree aggregation process for federated learning