Postdoctoral Researcher, University of Granada, Spain
Dr. Nuria Rodríguez-Barroso is a dedicated computer scientist and researcher at the University of Granada, affiliated with the Andalusian Research Institute in Data Science and Computational Intelligence 🇪🇸. With a strong academic foundation and an emerging reputation in the fields of Federated Learning and cybersecurity, she is recognized for her impactful work in making artificial intelligence more trustworthy and secure. Her innovative contributions to adversarial defense mechanisms and collaborative machine learning have positioned her as a promising young scientist in the AI research community 🧠💻.
Publication Profile
Google Scholar
🎓 Education Background
Dr. Rodríguez-Barroso completed a rigorous double degree in Mathematics and Computer Science, followed by a Master’s in Data Science, all from the University of Granada. She then earned an international Ph.D. with honors, titled “Adversarial Attacks and Defenses in Federated Learning,” at the same institution. Her academic trajectory is a remarkable blend of theoretical depth and practical relevance in the evolving world of machine learning and cybersecurity 🎓📚.
🧑💼 Professional Experience
Currently affiliated with the University of Granada, Dr. Rodríguez-Barroso has actively contributed to research funded by INCIBE (National Institute of Cybersecurity). She has also collaborated with Serpa.ai, working on open-source platforms for Federated Learning. With over 10 peer-reviewed publications, including 5 D1 and 1 Q1 journals, and participation in international conferences, she is well-versed in both academic and applied research. She has collaborated with notable researchers such as Francisco Herrera, Javier Del Ser, and Weiping Ding, extending her impact globally 🌍📈.
🏆 Awards and Honors
Dr. Rodríguez-Barroso’s outstanding contributions in Federated Learning and cybersecurity have earned her international recognition. She holds an international Ph.D. with honors and has made notable contributions to high-impact journals. Her recent nomination for the Young Scientist Award further underscores her potential as a leading researcher in Trustworthy AI and secure distributed systems 🏅🔐.
🔬 Research Focus
Her primary research interests lie in Federated Learning, Trustworthy AI, Causal AI, adversarial attacks, and cybersecurity. She has led and contributed to research projects aimed at developing dynamic defenses against Byzantine attacks and enhancing data privacy in AI systems. Her frameworks such as Sherpa.ai and FLEX have provided significant strides in privacy-preserving and explainable machine learning 🛡️🤖.
📚 Conclusion
Dr. Nuria Rodríguez-Barroso is a rising star in the fields of AI and cybersecurity, consistently pushing boundaries in Federated Learning and privacy-focused AI. Her combination of theoretical knowledge, practical application, and collaborative spirit places her among the most promising young researchers in computer science. She continues to contribute meaningfully to the development of secure, ethical, and robust AI systems for the future 🌟💡.
📚 Top Publications with Notes
FLEX: FLEXible Federated Learning Framework, Information Fusion, 2025 – A D1 journal article outlining a robust and modular FL framework for practical applications.
Cited by: 20+ articles (anticipated surge post-2025)
Survey on federated learning threats: Concepts, taxonomy on attacks and defences, Information Fusion, 2023 – A highly cited and comprehensive review with impactful insights on FL vulnerabilities.
Cited by: 180+ articles
Federated Learning for Exploiting Annotators’ Disagreements in NLP, Transactions of the Association for Computational Linguistics, 2024 – Offers new perspectives on handling noisy labeling in federated environments.
Cited by: 30+ articles
Defense Strategy against Byzantine Attacks in FL, IEEE FUZZ-IEEE Conference Proceedings, 2024 – Introduces explainable strategies to counter adversarial agents in distributed AI systems.
Cited by: 10+ articles
Backdoor attacks-resilient aggregation for image classification, Knowledge-Based Systems, 2022 – Proposes a novel filtering method to prevent data poisoning in FL.
Cited by: 60+ articles
Federated Learning and Differential Privacy: Sherpa.ai FL framework, Information Fusion, 2020 – Lays foundational guidelines for privacy-preserving federated architectures.
Cited by: 110+ articles
Dynamic defense against poisoning attacks in FL, Future Generation Computer Systems, 2022 – Explores a defense model that adapts to evolving attack scenarios.
Cited by: 70+ articles