Open-World & Robust Machine Learning

Out-of-distribution detection, open-set recognition, uncertainty and robustness for safe deployment of ML models.

Known-class clusters inside a protective dome, with unfamiliar out-of-distribution samples outside it

Deployed models constantly face inputs unlike their training data. This line develops methods that let ML models know what they do not know: detecting out-of-distribution (OOD) inputs, recognizing unknown classes in data streams, quantifying uncertainty, and balancing performance, efficiency and robustness.

The topic grew out of two earlier lines of my work: concept drift in data streams, where the data distribution changes over time, and the adversarial robustness of time series and image classifiers. Since 2021 it has become a line of its own, and it is the subject of Aitor Martínez-Seras’s doctoral thesis on OOD detection in open-world machine learning (2024). The work covers:

  • definitions and taxonomies of what is unknown to a model;
  • OOD detection for conventional, spiking and object-detection networks, and in reinforcement learning;
  • open-set recognition in data streams;
  • uncertainty quantification with conformal prediction and topological data analysis;
  • domain generalization;
  • trade-offs between accuracy, efficiency and robustness when models are compressed for deployment.

Main contributions

Publications in this area (19)

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

2026

  1. Neural Networks
    On the Inherent Robustness of One-Stage Object Detection Against Out-of-Distribution Data
    Aitor Martínez-Seras, Javier Del Ser, Aitzol Olivares-Rad, Alain Andrés, and Pablo G. Bringas
    Neural Networks, 2026
  2. Communications in computer and information science
    On the Limitations of Neural Collapse for the Detection of Out-of-Distribution Observations: Can We Do Any Better?
    Erik B. Terres-Escudero, Javier Del Ser, and Pablo G. Bringas
    In Communications in computer and information science, 2026
  3. Results in Engineering
    Adaptive Conformalized RNN Ensembles for Uncertainty-Aware Motion Prediction of Floating Offshore Wind Turbines in Stochastic Marine Environments
    Pranjal Tamuly, Javier Del Ser, Hamed Fathnejat, and Vincenzo Nava
    Results in Engineering, 2026

2025

  1. Neurocomputing
    A Collaborative Content Moderation Framework for Toxicity Detection Based on Multitask Neural Networks and Conformal Estimates of Annotation Disagreement
    Guillermo Villate-Castillo, Javier Del Ser, and Borja Sanz
    Neurocomputing, 2025
  2. IEEE Transactions on Circuits and Systems for Video Technology
    Multi-Domain Adversarial Variational Bayesian Inference for Domain Generalization
    Zhifan Gao, Saidi Guo, Chenchu Xu, Jinglin Zhang, Mingming Gong, Javier Del Ser, and 1 more author
    IEEE Transactions on Circuits and Systems for Video Technology, 2025

2024

  1. Neurocomputing
    Managing the Unknown in Machine Learning: Definitions, Related Areas, Recent Advances, and Prospects
    Marcos Barcina-Blanco, Jesús L. Lobo, Pablo G. Bringas, and Javier Del Ser
    Neurocomputing, 2024
  2. International Joint Conference on Neural Networks (IJCNN)
    Advancing Towards Safe Reinforcement Learning over Sparse Environments with Out-of-Distribution Observations: Detection and Adaptation Strategies
    Aitor Martínez-Seras, Alain Andrés, and Javier Del Ser
    In International Joint Conference on Neural Networks (IJCNN), 2024
  3. Lecture notes in computer science
    Resilience to the Flowing Unknown: An Open Set Recognition Framework for Data Streams
    Marcos Barcina-Blanco, Jesús L. Lobo, Pablo G. Bringas, and Javier Del Ser
    In Lecture notes in computer science, 2024
  4. IEEE International Conference on Intelligent Transportation Systems (ITSC)
    On the Connection Between Neural Activations and Uncertainty in Object Detection Transformers Using Topological Data Analysis
    Javier Del Ser, Aitor Martínez-Seras, Ibai Laña, Miren Nekane Bilbao, Panagiotis Fafoutellis, and Eleni I. Vlahogianni
    In IEEE International Conference on Intelligent Transportation Systems (ITSC), 2024
  5. IEEE Transactions on Intelligent Transportation Systems
    Measuring the Confidence of Single-Point Traffic Forecasting Models: Techniques, Experimental Comparison, and Guidelines Toward Their Actionability
    Ibai Laña, Ignacio Inaki Olabarrieta, and Javier Del Ser
    IEEE Transactions on Intelligent Transportation Systems, 2024
  6. Knowledge-Based Systems
    Domain Generalized Person Reidentification Based on Skewness Regularity of Higher-Order Statistics
    Mingfu Xiong, Yang Xu, Ruimin Hu, Zhongyuan Wang, Javier Del Ser, Khan Muhammad, and 1 more author
    Knowledge-Based Systems, 2024
  7. 2024 International Joint Conference on Neural Networks (IJCNN)
    Balancing Performance, Efficiency and Robustness in Open-World Machine Learning via Evolutionary Multi-Objective Model Compression
    Javier Del Ser, A. Martinez-Seras, Miren Nekane Bilbao, J. L. Lobo, Ibai Laña, and F. Herrera
    In 2024 International Joint Conference on Neural Networks (IJCNN), 2024

2023

  1. Information Fusion
    A Novel Out-of-Distribution Detection Approach for Spiking Neural Networks: Design, Fusion, Performance Evaluation and Explainability
    Aitor Martínez-Seras, Javier Del Ser, Jesús L. Lobo, Pablo G. Bringas, and Nikola Kirilov Kasabov
    Information Fusion, 2023
  2. IEEE International Conference on Intelligent Transportation Systems (ITSC)
    Efficient Object Detection in Autonomous Driving Using Spiking Neural Networks: Performance, Energy Consumption Analysis, and Insights into Open-Set Object Discovery
    Aitor Martínez-Seras, Javier Del Ser, and Pablo G. Bringas
    In IEEE International Conference on Intelligent Transportation Systems (ITSC), 2023
  3. IEEE Conference on Artificial Intelligence (CAI)
    On the Connection Between Concept Drift and Uncertainty in Industrial Artificial Intelligence
    Jesús L. Lobo, Ibai Laña, Eneko Osaba, and Javier Del Ser
    In IEEE Conference on Artificial Intelligence (CAI), 2023
  4. Applied Soft Computing
    Multiobjective Evolutionary Pruning of Deep Neural Networks with Transfer Learning for Improving Their Performance and Robustness
    Javier Poyatos, Daniel Molina, Aitor Martínez-Seras, Javier Del Ser, and Francisco Herrera
    Applied Soft Computing, 2023

2022

  1. 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

2020

  1. Neural Networks
    Robust Image Classification Against Adversarial Attacks Using Elastic Similarity Measures Between Edge Count Sequences
    Izaskun Oregi, Javier Del Ser, Aritz Perez, and Jose A. Lozano
    Neural Networks, 2020

2018

  1. International Symposium on Intelligent and Distributed Computing
    Adversarial Sample Crafting for Time Series Classification with Elastic Similarity Measures
    Izaskun Oregi, Javier Del Ser, Aritz Perez, and Jose A. Lozano
    In International Symposium on Intelligent and Distributed Computing, 2018