Pedro Miguel Sánchez

Pedro Miguel Sánchez

Data Scientist and Researcher — Ph.D. in Computer Science. I currently work as a Data Scientist at Roche.

Sitemap

A list of all the posts and pages found on the site. For you robots out there, there is an XML version available for digesting as well.

Pages

Posts

Computer Networks 2024 Best Paper Award

1 minute read

Published:

I am honored to receive the 2024 Best Paper Award from Elsevier’s Computer Networks journal for our work on federated learning for malware detection in IoT.

Joining Funditec as Senior Researcher: A New Chapter

less than 1 minute read

Published:

After completing my postdoctoral stage at the University of Murcia, I am excited to share that I have joined Funditec (Advantx Technology Foundation) in Madrid as a Senior Researcher.

National Young Researcher Award in Computer Science 2024 – BBVA Foundation and SCIE

1 minute read

Published:

I am honored to have received one of the National Young Researcher Awards in Computer Science 2024, granted by the BBVA Foundation and the Spanish Scientific Society of Computer Science (SCIE). This recognition encourages me to continue exploring the frontiers of cybersecurity and trustworthy artificial intelligence.

portfolio

publications

A survey on device behavior fingerprinting: Data sources, techniques, application scenarios, and datasets

Published in IEEE Communications Surveys & Tutorials, 23(2), 1048–1077, 2021

Comprehensive review of behavioral fingerprinting for IoT devices, including techniques, data sources, and application domains.

Recommended citation: Sánchez Sánchez, Pedro Miguel et al. (2021). "A survey on device behavior fingerprinting: Data sources, techniques, application scenarios, and datasets." IEEE Communications Surveys & Tutorials, 23(2), 1048–1077.
Download Paper

A methodology to identify identical single-board computers based on hardware behavior fingerprinting

Published in Journal of Network and Computer Applications, 103579, 2023

Proposes a methodology to uniquely identify SBCs using low-level hardware performance features and Machine Learning.

Recommended citation: Sánchez Sánchez, Pedro Miguel et al. (2023). "A methodology to identify identical single-board computers based on hardware behavior fingerprinting." Journal of Network and Computer Applications, 103579.
Download Paper

Adversarial attacks and defenses on ML-and hardware-based IoT device fingerprinting and identification

Published in Future Generation Computer Systems, 152, 30–42, 2024

Analyzes adversarial robustness of ML and hardware-based fingerprinting methods for IoT device authentication.

Recommended citation: Sánchez Sánchez, Pedro Miguel et al. (2024). "Adversarial attacks and defenses on ML-and hardware-based IoT device fingerprinting and identification." Future Generation Computer Systems, 152, 30–42.
Download Paper

FederatedTrust: A solution for trustworthy federated learning

Published in Future Generation Computer Systems, 152, 83-98, 2024

FederatedTrust, a framework that enhances trustworthiness in federated learning by addressing privacy, security, and accountability challenges.

Recommended citation: Sánchez Sánchez, Pedro Miguel et al. (2024). "FederatedTrust: A solution for trustworthy federated learning." Future Generation Computer Systems, 152, 83-98.
Download Paper

Transfer Learning in Pre-Trained Large Language Models for Malware Detection Based on System Calls

Published in IEEE Military Communications Conference (MILCOM) 2024, 2024

This paper presents a novel framework leveraging pre-trained LLMs to classify malware based on system call data.

Recommended citation: Sánchez, P. M. S., Celdrán, A. H., Bovet, G., & Pérez, G. M. (2024, October). Transfer learning in pre-trained large language models for malware detection based on system calls. In MILCOM 2024-2024 IEEE Military Communications Conference (MILCOM) (pp. 853-858). IEEE.
Download Paper

ProFe: Communication-Efficient Decentralized Federated Learning via Distillation and Prototypes

Published in IEEE International Conference on Communications (ICC) 2025, 2025

ProFe introduces a novel communication optimization algorithm for decentralized federated learning (DFL) that combines knowledge distillation, prototype learning, and quantization techniques to enhance efficiency and performance.

Recommended citation: Sánchez Sánchez, Pedro Miguel, Martínez Beltrán, Enrique Tomás, Fernández Llamas, Miguel, Bovet, Gérôme, Martínez Pérez, Gregorio, & Huertas Celdrán, Alberto. (2025). "ProFe: Communication-Efficient Decentralized Federated Learning via Distillation and Prototypes." IEEE ICC 2025.
Download Paper

S-VOTE: Similarity-based Voting for Client Selection in Decentralized Federated Learning

Published in IEEE International Joint Conference on Neural Networks (IJCNN) 2025, 2025

S-VOTE proposes a decentralized client selection strategy based on similarity voting to improve convergence and performance in non-IID federated learning scenarios.

Recommended citation: Sánchez Sánchez, Pedro Miguel et al. (2025). "S-VOTE: Similarity-based Voting for Client Selection in Decentralized Federated Learning." IEEE IJCNN 2025.
Download Paper

talks

teaching

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015

This is a description of a teaching experience. You can use markdown like any other post.