Explainable & Trustworthy AI

XAI taxonomies, counterfactual explanations, and the path from AI principles to responsible systems and regulation.

A transparent neural network explains its flower classification to a researcher, with feature attributions and a privacy shield

How can people understand, trust and safely govern machine learning models? This research line builds the conceptual foundations of Explainable Artificial Intelligence (XAI) and Responsible AI, and develops new methods for explaining models in ways that are actionable and reliable.

My work on explainability started from a practical question in one of my application domains: what lies beneath the black-box models used for road traffic forecasting (Barredo Arrieta et al., 2019). It grew into the 2020 taxonomy of XAI concepts, methods and challenges toward responsible AI (Arrieta et al., 2020), one of the most cited papers in the field and the core of Alejandro Barredo Arrieta’s doctoral thesis. Since then the line has moved in three directions:

  1. from explainability to the broader notion of trustworthy AI, connecting principles, ethics, technical requirements, auditing and regulation such as the EU AI Act;
  2. new explanation methods (counterfactual, neuro-symbolic and perturbation-based explanations for object detectors and 3D data) and ways to measure the quality of explanations;
  3. explainability as a requirement in high-stakes domains such as medicine, industry, transportation and federated learning.

Much of this work is done with Andreas Holzinger (BOKU University), Francisco Herrera and Natalia Díaz-Rodríguez (University of Granada) and Luca Longo (Technological University Dublin).

Main contributions

Publications in this area (28)

All my publications related to this research line, in reverse chronological order, including those mentioned above.

2026

  1. Information Fusion
    A Design Framework for Operationalizing Trustworthy Artificial Intelligence in Healthcare: Requirements, Tradeoffs and Challenges for Its Clinical Adoption
    Pedro A. Moreno-Sánchez, Javier Del Ser, Mark Gils, and Jussi A. Hernesniemi
    Information Fusion, 2026

2025

  1. Machine Learning and Knowledge Extraction
    Research Frontiers in Machine Learning & Knowledge Extraction
    Andreas Holzinger, Luca Longo, Angelo Cangelosi, and Javier Del Ser
    Machine Learning and Knowledge Extraction, 2025
  2. Annual ADIA Lab Transactions in Data Science and Finance
    Trustworthy Artificial Intelligence: Nature, Requirements, Regulation, and Emerging Discussions
    Francisco Herrera, Andres Herrera, Javier Del Ser, Enrique Herrera‐Viedma, and Marcos López Prado
    In Annual ADIA Lab Transactions in Data Science and Finance, 2025
  3. Information Sciences
    Overlap Number of Balls Model-Agnostic CounterFactuals (ONB-MACF): A Data-Morphology-Based Counterfactual Generation Method for Trustworthy Artificial Intelligence
    José Daniel Pascual-Triana, Alberto Fernández, Javier Del Ser, and Francisco Herrera
    Information Sciences, 2025
  4. Information Fusion
    Enhancing Trust in Automated 3D Point Cloud Data Interpretation Through Explainable Counterfactuals
    Andreas Holzinger, Niko Lukač, Dzemail Rozajac, Emile Johnston, Veljka Kocic, Bernhard Hörl, and 5 more authors
    Information Fusion, 2025
  5. Expert Systems
    Explaining 3D Semantic Segmentation Through Generative AI -Based Counterfactuals
    Dzemail Rozajac, Niko Lukač, Stefan Schweng, Christoph Gollob, Arne Nothdurft, Karl Stampfer, and 2 more authors
    Expert Systems, 2025
  6. IEEE Access
    LLM in the Loop: A Framework for Contextualizing Counterfactual Segment Perturbations in Point Clouds
    Veljka Kočić, Niko Lukač, Dzemail Rozajac, Stefan Schweng, Christoph Gollob, Arne Nothdurft, and 3 more authors
    IEEE Access, 2025
  7. European Conference on Artificial Intelligence (ECAI)
    D-CRISP: Explaining Object Detectors by Combining Randomized and Segment-Based Perturbations
    A. Andres and Javier Del Ser
    In European Conference on Artificial Intelligence (ECAI), 2025
  8. Pattern Recognition
    The Level of Strength of an Explanation: A Quantitative Evaluation Technique for Post-Hoc XAI Methods
    Marilyn Bello, Rosalís Amador, María-Matilde García, Javier Del Ser, Pablo Mesejo, and Óscar Cordón
    Pattern Recognition, 2025
  9. Lecture notes in computer science
    Benchmarking Machine Learning Models for QoE Estimation in Video Streaming: Accuracy, Efficiency, Confidence and Explainability
    Miren Nekane Bilbao, Mikel Getino-Petit, and Javier Del Ser
    In Lecture notes in computer science, 2025

2024

  1. Information Fusion
    Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directions
    Luca Longo, Mario Brcic, Federico Cabitza, Jaesik Choi, Roberto Confalonieri, Javier Del Ser, and 13 more authors
    Information Fusion, 2024
  2. Information Sciences
    On Generating Trustworthy Counterfactual Explanations
    Javier Del Ser, Alejandro Barredo-Arrieta, Natalia Díaz-Rodríguez, F. Herrera, A. Saranti, and A. Holzinger
    Information Sciences, 2024
  3. Results in Engineering
    On the Black-Box Explainability of Object Detection Models for Safe and Trustworthy Industrial Applications
    Alain Andrés, Aitor Martínez-Seras, Ibai Laña, and Javier Del Ser
    Results in Engineering, 2024
  4. IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)
    Defense Strategy Against Byzantine Attacks in Federated Machine Learning: Developments Towards Explainability
    Nuria Rodríguez-Barroso, Javier Del Ser, M. Victoria Luzón, and Francisco Herrera
    In IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), 2024

2023

  1. Information Fusion
    Explainable Artificial Intelligence (XAI): What We Know and What Is Left to Attain Trustworthy Artificial Intelligence
    Sajid Ali, Tamer Abuhmed, Shaker El-Sappagh, Khan Muhammad, Jose M Alonso-Moral, Roberto Confalonieri, and 4 more authors
    Information Fusion, 2023
  2. Information Fusion
    Connecting the Dots in Trustworthy Artificial Intelligence: From AI Principles, Ethics, and Key Requirements to Responsible AI Systems and Regulation
    Natalia Díaz-Rodríguez, Javier Del Ser, Mark Coeckelbergh, Marcos López De Prado, Enrique Herrera-Viedma, and Francisco Herrera
    Information Fusion, 2023
  3. IEEE Conference on Artificial Intelligence (CAI)
    The Right to Be Forgotten in Artificial Intelligence: Issues, Approaches, Limitations and Challenges
    Jesús L. Lobo, Sergio Gil-López, and Javier Del Ser
    In IEEE Conference on Artificial Intelligence (CAI), 2023
  4. IEEE Transactions on Emerging Topics in Artificial Intelligence
    Explainable COVID-19 Infections Identification and Delineation Using Calibrated Pseudo Labels
    Ming Li, Yingying Fang, Zeyu Tang, Chibudom Onuorah, Jun Xia, Javier Del Ser, and 2 more authors
    IEEE Transactions on Emerging Topics in Artificial Intelligence, 2023
  5. Information Fusion
    Prediction of Alzheimer’s Progression Based on Multimodal Deep-Learning-Based Fusion and Visual Explainability of Time-Series Data
    Nasir Rahim, Shaker El-Sappagh, Sajid Ali, Khan Muhammad, Javier Del Ser, and Tamer Abuhmed
    Information Fusion, 2023

2022

  1. Knowledge-Based Systems
    Greybox XAI: A Neural-Symbolic Learning Framework to Produce Interpretable Predictions for Image Classification
    Adrien Bennetot, Gianni Franchi, Javier Del Ser, Raja Chatila, and Natalia Díaz-Rodríguez
    Knowledge-Based Systems, 2022
  2. Neural Computing and Applications
    On the Post-Hoc Explainability of Deep Echo State Networks for Time Series Forecasting, Image and Video Classification
    Alejandro Barredo Arrieta, Sergio Gil-Lopez, Ibai Laña, Miren Nekane Bilbao, and Javier Del Ser
    Neural Computing and Applications, 2022
  3. International Workshop on Soft Computing Models in Industrial and Environmental Applications
    Performance and Explainability of Reservoir Computing Models for Industrial Prognosis
    Unai Armentia, Irantzu Barrio, and Javier Del Ser
    In International Workshop on Soft Computing Models in Industrial and Environmental Applications, 2022
  4. 2022 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)
    Can Post-Hoc Explanations Effectively Detect Out-of-Distribution Samples?
    Aitor Martinez, Javier Del Ser, and Pablo Garcia-Bringas
    In 2022 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), 2022
  5. Information Fusion
    Information Fusion as an Integrative Cross-Cutting Enabler to Achieve Robust, Explainable, and Trustworthy Medical Artificial Intelligence
    Andreas Holzinger, Matthias Dehmer, Frank Emmert-Streib, Rita Cucchiara, Isabelle Augenstein, Javier Del Ser, and 3 more authors
    Information Fusion, 2022
  6. Future Generation Computer Systems
    Vessel-GAN: Angiographic Reconstructions from Myocardial CT Perfusion with Explainable Generative Adversarial Networks
    Chulin Wu, Heye Zhang, Jiaqi Chen, Zhifan Gao, Pengfei Zhang, Khan Muhammad, and 1 more author
    Future Generation Computer Systems, 2022

2021

  1. arXiv preprint arXiv:2104.00950
    Explainable Artificial Intelligence (XAI) on Time Series Data: A Survey
    Thomas Rojat, Raphaël Puget, David Filliat, Javier Del Ser, Rodolphe Gelin, and Natalia Díaz-Rodríguez
    arXiv preprint arXiv:2104.00950, 2021

2020

  1. Information Fusion
    Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges Toward Responsible AI
    Alejandro Barredo Arrieta, Natalia Díaz-Rodríguez, Javier Del Ser, Adrien Bennetot, Siham Tabik, Alberto Barbado, and 6 more authors
    Information Fusion, 2020

2019

  1. IEEE International Conference on Intelligent Transportation Systems (ITSC)
    What Lies Beneath: A Note on the Explainability of Black-Box Machine Learning Models for Road Traffic Forecasting
    Alejandro Barredo Arrieta, Ibai Laña, and Javier Del Ser
    In IEEE International Conference on Intelligent Transportation Systems (ITSC), 2019