Pedro Miguel Sanchez Sanchez
Scholar

Pedro Miguel Sanchez Sanchez

Google Scholar ID: RMS2xxkAAAAJ
Data Scientist, Roche
Anomaly DetectionFederated LearningTrustworthy AIIoTDistributed AI
Citations & Impact
All-time
Citations
2,018
 
H-index
19
 
i10-index
32
 
Publications
20
 
Co-authors
19
list available
Publications
20 items
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
  • Published multiple peer-reviewed papers, participated in numerous conferences and projects, detailed academic achievements can be found in the publications, talks, and projects sections of his personal website.
Research Experience
  • During the last stage of his PhD and post-PhD, shifted towards cutting-edge topics such as Decentralized Federated Learning, adversarial robustness, and AI model explainability, contributing to European defense and digital sovereignty through projects. Then moved to Funditec, focusing on applied ML/DL and cybersecurity research, along with preparation of European and National research grants, project execution, and administration. Currently working as a Data Scientist at Roche, applying AI across various business use cases.
Education
  • Earned a B.Sc. and M.Sc. in Computer Science from the University of Murcia, specializing in secure continuous authentication for smart devices; later obtained a Ph.D. in Computer Science (Cum Laude) from the same institution, with doctoral research centered on behavioral fingerprinting of IoT devices for identification and attack detection using Machine and Deep Learning, conducted in collaboration with armasuisse S&T in Switzerland.
Background
  • Data Scientist and Researcher, specializing in Artificial Intelligence, Federated Learning, and Cybersecurity. Working at Roche, focusing on trustworthy AI and decentralized learning paradigms, particularly secure, fair, and robust deployment of intelligent systems in IoT and critical infrastructure environments.
Miscellany
  • Interested in building secure AI systems and federated learning architectures, open to collaborations or project proposals related to these areas.