EDBT 2026 Demo / reviewers in the wild / expert
Nicolas Atienza
dblp:388/1752
· DBLP profile ↗
2ranked-venue papers
2as first author
2since 2021 · last 2025
—ORCID · none
Domains — the database's venue-derived domains; a paper can count in several
Artificial intelligence and machine learning · 2 · 2 first-author · 2 since 2021Graphics, computer vision, multimedia, augmented reality and games · 1 · 1 first-author · 1 since 2021
Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.
| Artificial intelligence
2 papers |
Trustworthy machine learning · 93% Probabilistic and Bayesian machine learning · 7% |
Topics — the 5 heaviest of 5, each with the papers that count most for it
| Topic | Weight | Papers | Last | Evidence papers |
|---|---|---|---|---|
Machine learning › Trustworthy machine learning › robustness
adversarial robustness |
0.9 | 1 | 2025 | Provably Safeguarding a Classifier from OOD and Adversarial Samples · ICLR 2025 |
Machine learning › Trustworthy machine learning › robustness
out-of-distribution detection |
0.9 | 1 | 2025 | Provably Safeguarding a Classifier from OOD and Adversarial Samples · ICLR 2025 |
Machine learning › Trustworthy machine learning
robustness |
0.9 | 1 | 2025 | Provably Safeguarding a Classifier from OOD and Adversarial Samples · ICLR 2025 |
Machine learning › Trustworthy machine learning
interpretability |
0.8 | 1 | 2024 | Cutting the Black Box: Conceptual Interpretation of a Deep Neural Net with Multi-Modal Embeddings and Multi-Criteria Decision Aid · IJCAI 2024 |
Machine learning › Probabilistic and Bayesian machine learning
extreme value theory |
0.3 | 1 | 2025 | Provably Safeguarding a Classifier from OOD and Adversarial Samples · ICLR 2025 |
Methods — techniques the papers use, named apart from their topics
latent space modeling · 0.9generalized extreme value model · 0.9multimodal embedding · 0.8multi-criteria decision aid · 0.8
| Year | Publication | Venue | Position |
|---|---|---|---|
| 2025 | Provably Safeguarding a Classifier from OOD and Adversarial SamplesabstractThis paper aims to transform a trained classifier into an abstaining classifier, such
that the latter is provably protected from out-of-distribution and adversarial samples. The proposed Sample-efficient Probabilistic Detection using Extreme Value
Theory (SPADE) approach relies on a Generalized Extreme Value (GEV) model
of the training distribution in the latent space of the classifier. Under mild assumptions, this GEV model allows for formally characterizing out-of-distribution
and adversarial samples and rejecting them. Empirical validation of the approach
is conducted on various neural architectures (ResNet, VGG, and Vision Transformer) and considers medium and large-sized datasets (CIFAR-10, CIFAR-100,
and ImageNet). The results show the stability and frugality of the GEV model and
demonstrate SPADE’s efficiency compared to the state-of-the-art methods. Nicolas Atienza, Johanne Cohen, Christophe Labreuche, Michèle Sebag |
ICLR | 1 |
| 2024 | Cutting the Black Box: Conceptual Interpretation of a Deep Neural Net with Multi-Modal Embeddings and Multi-Criteria Decision Aid
Nicolas Atienza, Roman Bresson, Cyriaque Rousselot, Philippe Caillou, Johanne Cohen, Christophe Labreuche, Michèle Sebag |
IJCAI | 1 |