Publications

2025

Nikolaos Antonios Grammatikos, Evangelia Anagnostopoulou , Dimitris Apostolou and Gregoris Mentzas

Towards Trustworthy AI in STEM Education: Challenges and Strategies from the Trust-AI Platform

Trust-AI Workshop of ECAI

2025

Kitty Kioskli, Theofanis Fotis, Eleni Seralidou, Marios Passaris and Nineta Polemi

trustSense: Measuring Human Oversight Maturity for Trustworthy AI

Computers 2025, 14(11), 483;

2025

G. Del Corso, S. Colantonio, C. Caudai

Shedding light on uncertainties in machine learning: formal derivation and optimal model selection

Journal of the Franklin Institute 362(2–3):107548,

2025

V. Pezoulas

Fairness Through Synthesis: Bias Mitigation Through Probabilistic Modeling and Matching Techniques

4th Serbian International Conference on Applied Artificial Intelligence

2025

Pezoulas, V. C., Tachos, N. S., Zaridis, D. I., Chatzis, L., Goules, A., Marias, K., Tsiknakis, M., Tzioufas A. G., and Fotiadis, D.

A synthetic data-driven generation approach to enhance the fairness and privacy of AI-based systems in the domain of rare diseases

IEEE BHI conference 2025

2025

Apostolidis, K., Zaridis, D. I., Tachos, N. S., Pezoulas, V. C., Marias, K., Tsiknakis, M., and Fotiadis, D

Adversarial Robustness Evaluation of Deep Learning Segmentation Models and Loss Functions in Prostate MRI

IEEE BHI conference 2025

2025

Seralidou, E.; Kioskli, K.; Fotis, T.; Polemi

AI_TAF: A Human-Centric Trustworthiness Risk Assessment Framework for AI Systems

2025

Explanations for Trustworthy AI in Critical Infrastructure: A Case from Wastewater Treatment in Norway

2025

Kitty Kioskli, Elisavet Grigoriou, Shareeful Islam, Andrianos M. Yiorkas, Loizos Christofi & Haralambos Mouratidis

A risk and conformity assessment framework to ensure security and resilience of healthcare systems and medical supply chain

2025

Kitty Kioskli ,Eleni Seralidou and Nineta Polemi

A Practical Human-Centric Risk Management (HRM) Methodology

Electronics 2025, 14(3), 486;