Alberto Gutierrez-Torre
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Alberto Gutierrez-Torre has a total of 115 co-authors. Here are the top co-authors by number of shared publications:
- Josep Lluis Berral
Universitat Politecnica de Catalunya
8 shared publications - David Carrera
Barcelona Supercomputing Center (BSC)
4 shared publications - Ferran Agullo
Barcelona Supercomputing Center
4 shared publications - Jordi Torres
Barcelona Supercomputing Center
3 shared publications - Ahmed Youssef Ali Amer
E-MEDIA, STADIUS, Department of Electrical Engineering (ESAT), Campus Group T, KU Leuven, 3000 Leuven, Belgium
2 shared publications - Andreas Charalambous
Cyprus University of Technology
2 shared publications
Latest Publications
- Open Access
- 1 November 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 355
In-context bias propagation in LLM-based tabular data generation
- 1 November 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 355
Open AccessIn-context bias propagation in LLM-based tabular data generation
- Open Access
- 21 August 2026
- Published by Elsevier in Future Generation Computer Systems
- Vol. 186
Data-driven optimization of GPU efficiency for distributed LLM-adapter serving
- 21 August 2026
- Published by Elsevier in Future Generation Computer Systems
- Vol. 186
Open AccessData-driven optimization of GPU efficiency for distributed LLM-adapter serving
- 7 January 2026
- Published by Elsevier in Seminars in Oncology Nursing
- Vol. 42 (1) , 152088
Evaluation of the INCISIVE Services in Cancer Imaging: A Feasibility Study
- 7 January 2026
- Published by Elsevier in Seminars in Oncology Nursing
- Vol. 42 (1) , 152088
Evaluation of the INCISIVE Services in Cancer Imaging: A Feasibility Study
- Open Access
- 30 December 2025
- Published by Elsevier in Journal of Information Security and Applications
- Vol. 97
FRIDA: Free-rider detection using privacy attacks
- 30 December 2025
- Published by Elsevier in Journal of Information Security and Applications
- Vol. 97
Open AccessFRIDA: Free-rider detection using privacy attacks
- Open Access
- 17 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 195871-195903
SynthVal : A Framework for Validating Synthetic Medical Images
Synthetic data is increasingly used in medical imaging to overcome data scarcity and privacy constraints. However, assessing the fidelity of synthetic images remains a critical challenge for ensuring their safe and effective use in clinical and AI applications. We present SynthVal, a Python-based framework for validating the quality of synthetic medical images through statistical comparisons in deep feature space. SynthVal extracts semantic image embeddings using transformer-based models and computes similarity metrics – including Fréchet Distance, Wasserstein Distance, and Kullback-Leibler Divergence – between real and synthetic data distributions. The framework is designed for modularity, scalability, and ease of integration into existing workflows via pip installation. We evaluate SynthVal using real images from the CSAW-CC dataset, and synthetic images produced by a model developed by the Barcelona Supercomputing Center. Our experiments systematically benchmark the influence of different feature extraction models and similarity metrics, providing practical insights for selecting validation strategies in medical image synthesis. SynthVal offers a reproducible and extensible solution for quality control in synthetic data pipelines.
- 17 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 195871-195903
Open AccessSynthVal : A Framework for Validating Synthetic Medical Images
Synthetic data is increasingly used in medical imaging to overcome data scarcity and privacy constraints. However, assessing the fidelity of synthetic images remains a critical challenge for ensuring their safe and effective use in clinical and AI applications. We present SynthVal, a Python-based framework for validating the quality of synthetic medical images through statistical comparisons in deep feature space. SynthVal extracts semantic image embeddings using transformer-based models and computes similarity metrics – including Fréchet Distance, Wasserstein Distance, and Kullback-Leibler Divergence – between real and synthetic data distributions. The framework is designed for modularity, scalability, and ease of integration into existing workflows via pip installation. We evaluate SynthVal using real images from the CSAW-CC dataset, and synthetic images produced by a model developed by the Barcelona Supercomputing Center. Our experiments systematically benchmark the influence of different feature extraction models and similarity metrics, providing practical insights for selecting validation strategies in medical image synthesis. SynthVal offers a reproducible and extensible solution for quality control in synthetic data pipelines.
- Open Access
- 1 September 2025
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 28, e83369
Rethinking Trust in Synthetic Health Data: Lessons from Seven European Research Initiatives (Preprint)
Synthetic data generation (SDG) structured health data is increasingly promoted as a solution to longstanding barriers in health data access. It is offering the promise of privacy-preserving data reuse for research, innovation, and policy. Despite rapid technical advances, the adoption of synthetic health data in real-world settings remains limited. Shaped by challenges around data quality, representativeness, infrastructure readiness, trust, and legal uncertainty, this viewpoint draws on experiences from 7 European research initiatives within the HealthData4EU cluster to reflect on how SDG is being operationalized in practice. It synthesizes cross-project insights to highlight recurring methodological and governance tensions and to examine their implications for trust and responsible use. The analysis argues that trustworthy SDG cannot be achieved through technical optimization alone but requires alignment between evaluation practices, upstream data stewardship, regulatory clarity, and sustained stakeholder engagement. Addressing these conditions is essential for moving synthetic data from experimental pilots toward a credible and sustainable component of European health research ecosystems.
- 1 September 2025
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 28, e83369
Open AccessRethinking Trust in Synthetic Health Data: Lessons from Seven European Research Initiatives (Preprint)
Synthetic data generation (SDG) structured health data is increasingly promoted as a solution to longstanding barriers in health data access. It is offering the promise of privacy-preserving data reuse for research, innovation, and policy. Despite rapid technical advances, the adoption of synthetic health data in real-world settings remains limited. Shaped by challenges around data quality, representativeness, infrastructure readiness, trust, and legal uncertainty, this viewpoint draws on experiences from 7 European research initiatives within the HealthData4EU cluster to reflect on how SDG is being operationalized in practice. It synthesizes cross-project insights to highlight recurring methodological and governance tensions and to examine their implications for trust and responsible use. The analysis argues that trustworthy SDG cannot be achieved through technical optimization alone but requires alignment between evaluation practices, upstream data stewardship, regulatory clarity, and sustained stakeholder engagement. Addressing these conditions is essential for moving synthetic data from experimental pilots toward a credible and sustainable component of European health research ecosystems.
- Open Access
- 1 September 2025
- Published by JMIR Publications Inc. in JMIR Preprints
Building Trust in Synthetic Health Data: Methodological and Acceptance Challenges across Seven European Projects (Preprint)
BACKGROUND Synthetic data generation (SDG) is increasingly used in health research to address privacy concerns and data sharing barriers, particularly in cross-border and multi-institutional contexts. Despite growing interest, questions remain around the methodological soundness, legal status, and real-world trustworthiness of synthetic health data. OBJECTIVE This paper examines how SDG is operationalized across seven European projects in the HealthData4EU cluster. It identifies common methodological, compliance, and acceptance challenges, and highlights emerging strategies to ensure the quality and utility of synthetic health data. METHODS A qualitative multiple case study approach was used, combining workshop presentations with structured input from each project. Projects were analyzed across four aspects: methodological challenges, data quality assurance, trust and transparency strategies, and contributions to the wider synthetic data ecosystem. RESULTS Results reveal recurring challenges across projects: tension between privacy and utility, lack of shared quality validation standards, institutional readiness gaps, and legal ambiguity under GDPR. Projects employ varied strategies, including federated machine learning and validation pipelines, differential privacy, co-design processes, and metadata transparency tools, but implementation remains uneven. The absence of harmonised legal and evaluation frameworks continues to hinder broader uptake. CONCLUSIONS To scale SDG from isolated pilots to trusted European infrastructure, four priorities are critical: shared evaluation metrics, legal clarity, sustainable platforms, and embedded stakeholder engagement. While rooted in specific projects, the insights offer broader relevance for global SDG efforts, as the core tensions identified are likely to recur across health systems.
- 1 September 2025
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessBuilding Trust in Synthetic Health Data: Methodological and Acceptance Challenges across Seven European Projects (Preprint)
BACKGROUND Synthetic data generation (SDG) is increasingly used in health research to address privacy concerns and data sharing barriers, particularly in cross-border and multi-institutional contexts. Despite growing interest, questions remain around the methodological soundness, legal status, and real-world trustworthiness of synthetic health data. OBJECTIVE This paper examines how SDG is operationalized across seven European projects in the HealthData4EU cluster. It identifies common methodological, compliance, and acceptance challenges, and highlights emerging strategies to ensure the quality and utility of synthetic health data. METHODS A qualitative multiple case study approach was used, combining workshop presentations with structured input from each project. Projects were analyzed across four aspects: methodological challenges, data quality assurance, trust and transparency strategies, and contributions to the wider synthetic data ecosystem. RESULTS Results reveal recurring challenges across projects: tension between privacy and utility, lack of shared quality validation standards, institutional readiness gaps, and legal ambiguity under GDPR. Projects employ varied strategies, including federated machine learning and validation pipelines, differential privacy, co-design processes, and metadata transparency tools, but implementation remains uneven. The absence of harmonised legal and evaluation frameworks continues to hinder broader uptake. CONCLUSIONS To scale SDG from isolated pilots to trusted European infrastructure, four priorities are critical: shared evaluation metrics, legal clarity, sustainable platforms, and embedded stakeholder engagement. While rooted in specific projects, the insights offer broader relevance for global SDG efforts, as the core tensions identified are likely to recur across health systems.
- 10 July 2025
- Published by Springer Nature
- p. 169-194
Architectures and Platforms for Trustworthy AI: Cloud Technologies and Federated Approaches
- 10 July 2025
- Published by Springer Nature
- p. 169-194
Architectures and Platforms for Trustworthy AI: Cloud Technologies and Federated Approaches
- Open Access
- 4 April 2025
- Published by Elsevier in Future Generation Computer Systems
- Vol. 170
Enhancing the output of time series forecasting algorithms for cloud resource provisioning
- 4 April 2025
- Published by Elsevier in Future Generation Computer Systems
- Vol. 170
Open AccessEnhancing the output of time series forecasting algorithms for cloud resource provisioning
- Open Access
- 2 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 117-130
Dexter: A Performance-Cost Efficient Resource Allocation Manager for Serverless Data Analytics
Leveraging serverless platforms for the efficient execution of distributed data analytics frameworks, such as Apache Spark [3], has gained substantial interest since early 2022. The elasticity, free-of-management, and on-demand scalability of serverless have motivated the effort in deploying distributed data analytics applications to serverless platforms. However, effectively auto-scaling resources for such complex workloads so that we can fully benefit from the resource elasticity of serverless remains challenging. Mis-configuration can result in severe performance and cost issues arising from resource under- and over-provisioning. In this paper, we present Dexter, a robust resource allocation manager dynamically allocating resources at a fine-grained level to guarantee performance-cost efficiency (optimizing total runtime cost). Dexter is novel in combining predictive and reactive strategies that fully leverage the elasticity of serverless to enhance the performance-cost efficiency for workflow executions. Unlike black-box ML models, Dexter quickly reaches a sufficiently good solution, prioritizing simplicity, generality, and ease of understanding. Our experimental evaluation shows that, compared with the default serverless Spark resource allocation that dynamically requests exponentially more executors to accommodate pending tasks, our solution achieves a cost reduction of up to 4.65×, while improving performance-cost efficiency up to 3.50×. Dexter also enables a substantial resource saving, demanding up to 5.75× fewer resources.
- 2 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 117-130
Open AccessDexter: A Performance-Cost Efficient Resource Allocation Manager for Serverless Data Analytics
Leveraging serverless platforms for the efficient execution of distributed data analytics frameworks, such as Apache Spark [3], has gained substantial interest since early 2022. The elasticity, free-of-management, and on-demand scalability of serverless have motivated the effort in deploying distributed data analytics applications to serverless platforms. However, effectively auto-scaling resources for such complex workloads so that we can fully benefit from the resource elasticity of serverless remains challenging. Mis-configuration can result in severe performance and cost issues arising from resource under- and over-provisioning. In this paper, we present Dexter, a robust resource allocation manager dynamically allocating resources at a fine-grained level to guarantee performance-cost efficiency (optimizing total runtime cost). Dexter is novel in combining predictive and reactive strategies that fully leverage the elasticity of serverless to enhance the performance-cost efficiency for workflow executions. Unlike black-box ML models, Dexter quickly reaches a sufficiently good solution, prioritizing simplicity, generality, and ease of understanding. Our experimental evaluation shows that, compared with the default serverless Spark resource allocation that dynamically requests exponentially more executors to accommodate pending tasks, our solution achieves a cost reduction of up to 4.65×, while improving performance-cost efficiency up to 3.50×. Dexter also enables a substantial resource saving, demanding up to 5.75× fewer resources.