David Sánchez

Full Professor and ICREA Academia

Tel: +34 977 55 9657

Email: david.sanchez@urv.cat

Research Lines

Trustworthy AI

Secure and Robust AI Privacy-Preserving AI Explainable AI Fairness and Bias Unlearning

Data Privacy

Data Anonymization Differential Privacy Privacy in Machine Learning Federated Learning Privacy-Preserving Data Analysis Privacy Risk Assessment and Auditing

Academic Profiles

ORCID Google Scholar

Publications

View all →

2026 Journal Q1 To Appear

Unsupervised utility evaluation of text anonymization methods via neural language models

NEURAL NETWORKS

B. Manzanares-Salor, D. Sánchez and P. Lison

DOI PDF BibTeX

2026 Journal D1 To Appear

FSCL-BC: Federated supervised contrastive learning for breast cancer diagnosis with high sensitivity

COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE

F. Ahmed, D. Sánchez, Z. Haddi and J. Domingo-Ferrer

DOI PDF BibTeX

2026 Conference Core A To Appear

A Critical Review on the Effectiveness and Privacy Threats of Membership Inference Attacks

ESORICS 2026

N. Jebreel, D. Sánchez, and J. Domingo-Ferrer

PDF

2026 Conference Core A To Appear

Revisiting the LiRA Membership Inference Attack Under Realistic Assumptions

PETS2026

N. Jebreel, M. Khalil, D. Sánchez, J. Domingo-Ferrer

DOI PDF BibTeX

2026 Journal D1 To Appear

FedGA: Genetic Algorithm-Guided Federated Learning for Medical Image Segmentation with Non-IID Features

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS

F. Ahmed, R. Moreno, D. Sánchez; Z. Haddi and J. Domingo-Ferrer

DOI PDF BibTeX

2026 Journal

TAE: Text anonymization evaluator

SOFTWAREX

B. Manzanares-Salor, D. Sánchez, P. Lison and I. Pilán

DOI BibTeX

2026 Conference

Explainability-driven anonymization in latent space (EDIALS)

CODASPY 2026

Y. Khan, A. Monreale, C. Metta, D. Sánchez and J. Domingo-Ferrer

DOI PDF BibTeX

2026 Journal Q1

A comparative analysis, enhancement and evaluation of text anonymization with pre-trained Large Language Models

EXPERT SYSTEMS WITH APPLICATIONS

B. Manzanares-Salor and D. Sánchez

DOI PDF BibTeX

2026 Journal

Differential privacy in practice: lessons learned from 10 years of real-world applications

IEEE SECURITY & PRIVACY

L. Del Vasto-Terrientes, D. Sánchez and J. Domingo-Ferrer

DOI PDF BibTeX

2025 Journal Q1

DP2Unlearning: An efficient and guaranteed unlearning framework for LLMs

NEURAL NETWORKS

T. Al Mahmud, N. Jebreel, J. Domingo-Ferrer and D. Sánchez

DOI PDF BibTeX

2025 Journal Q1

Truthful text sanitization guided by inference attacks

APPLIED SOFT COMPUTING

I. Pilán, B. Manzanares-Salor, D. Sánchez and P. Lison

DOI PDF BibTeX

2025 Journal

Anonymization did not fail: misconceptions and overstatements on data anonymization failures

IEEE SECURITY & PRIVACY

D. Sánchez, J. Domingo-Ferrer and K. Muralidhar

DOI PDF BibTeX

2025 Journal

Explainability-Driven Incremental Image Anonymization

TRANSACTIONS ON DATA PRIVACY

R. Haffar, D. Sánchez, Y. Khan and J. Domingo-Ferrer

PDF

2025 Conference

Defenses against membership inference attacks on unlearned data

MDAI2025

J. Domingo-Ferrer, N. Jebreel and D. Sánchez

DOI PDF BibTeX

2025 Conference

FedBC: Privacy-preserving breast cancer diagnosis from ultrasound images using federated learning

BREATH 2025

F. Ahmed, D. Sánchez, J. Domingo-Ferrer and Z. Haddi

DOI PDF BibTeX

2025 Conference

LFighter: Defending Against the Label-Flipping Attack in Federated Learning (Extended Abstract)

ECMLPKDD 2025

N. Jebreel, J. Domingo-Ferrer, D. Sánchez, A. Blanco-Justicia

2025 Journal

Statistical disclosure control: moving forward

JOURNAL OF OFFICIAL STATISTICS

J. Domingo-Ferrer, D. Sánchez and K. Muralidhar

DOI PDF BibTeX

2025 Journal Q1

Enhancing efficiency and data utility in longitudinal data anonymization

INFORMATION SCIENCES

F. Amiri, D. Sánchez and J. Domingo-Ferrer

DOI PDF BibTeX

2025 Journal

Multi-task (MTF) data set: a legally and ethically compliant collection of face images for various classification tasks

IEEE ACCESS

R.Haffar, D. Sánchez and J. Domingo-Ferrer

DOI BibTeX

2025 Journal D1

Digital forgetting in large language models: a survey of unlearning models

ARTIFICIAL INTELLIGENCE REVIEW

A. Blanco-Justicia, N. Jebreel, B. Manzanares-Salor, D. Sánchez, J. Domingo-Ferrer, G. Collell and K. E. Tan

DOI PDF BibTeX

2025 Journal Q1

Enhancing text anonymization via re-identification risk-based explainability

KNOWLEDGE-BASED SYSTEMS

B. Manzanares-Salor and D. Sánchez

DOI PDF BibTeX

2025 Journal Q1

MemberShield: a framework for federated learning with membership privacy

NEURAL NETWORKS

F. Ahmed, D. Sánchez, Z. Haddi and J. Domingo-Ferrer

DOI BibTeX

2025 Journal

Protecting vulnerable respondents: a critical analysis of the privacy-preserving methods of the 2010 and 2020 Decennial Census

POPULATION RESEARCH AND POLICY REVIEW

K. Muralidhar, J. Domingo-Ferrer, D. Sánchez and S. Ruggles

DOI PDF BibTeX

2025 Journal

Unlearning in Large Language Models: We Are Not There Yet

COMPUTER

A. Blanco-Justicia, J. Domingo-Ferrer, N. M. Jebreel, B. Manzanares-Salor and D. Sánchez

DOI PDF BibTeX

2025 Journal

Conciliating Privacy and Utility in Data Releases via Individual Differential Privacy and Microaggregation

TRANSACTIONS ON DATA PRIVACY

J. Soria-Comas, D. Sánchez, J. Domingo-Ferrer, S. Martínez and L. Del Vasto-Terrientes

PDF

2024 Journal D1

Federated learning-based natural language processing: a systematic literature review

ARTIFICIAL INTELLIGENCE REVIEW

Y Khan, D. Sánchez and J. Domingo-Ferrer

DOI BibTeX

2024 Conference

Armonizando Privacidad y Utilidad en la Publicación de Datos mediante Privacidad Diferencial Individual y Microagregación

RECSI 2024

J. Soria-Comas, D. Sánchez, J. Domingo-Ferrer, S. Martínez and L. Del Vasto-Terrientes

PDF

2024 Conference

Enhanced Security and Privacy via Fragmented Federated Learning

RECSI 2024

N. Jebreel, J. Domingo-Ferrer, A. Blanco-Justicia and D. Sánchez

PDF

2024 Journal

Evaluating the disclosure risk of anonymized documents via a machine learning-based re-identification attack

DATA MINING AND KNOWLEDGE DISCOVERY

B. Manzanares-Salor, D. Sánchez and P. Lison

DOI PDF BibTeX

2024 Conference

An examination of the alleged privacy threats of confidence-ranked reconstruction of Census microdata

PSD 2024

D. Sánchez, N. Jebreel, K. Muralidhar, J. Domingo-Ferrer, and A. Blanco-Justicia

DOI PDF BibTeX