Scientific Publications

MultiLeg: Dataset for Text Sanitisation in Less-resourced Languages
Analyzing the European institutional response to ethical and regulatory challenges of artificial intelligence in addressing discriminatory bias
Efficient visual information indexation for supporting actionable intelligence and knowledge generation
IM-DISCO: Invariant Mining for Detecting IntrusionS in Critical Operations
Identification of key actor nodes: A centrality measure ranking aggregation approach.
Explainability versus Security: The Unintended Consequences of xAI in Cybersecurity.
Discriminatory bias (and how to prevent it) in the European Union: a review of the ethical and regulatory framework for artificial intelligence.
Bias Detection and Mitigation in Textual Data: A Study on Fake News and Hate Speech Detection.
Trend Detection in Crime-Related Time Series with Change Point Detection Methods
A Cybersecurity Risk Analysis Framework for Systems with Artificial Intelligence Components
Protecting Classifiers from Attacks
MobilityDL: A Review of Deep Learning From Trajectory Data
Towards eXplainable AI for Mobility Data Science
Wider or Deeper Neural Network Architecture for Acoustic Scene Classification with Mismatched Recording Devices
Light-Weight Deep Learning Models for Acoustic Scene Classification Using Teacher-Student Scheme and Multiple Spectrograms
Deep learning based multimodal with two-phase training strategy for daily life video classification.
Lightweight deep neural networks for acoustic scene classification and an effective visualization for presenting sound scene contexts.
De-identifying Face Image Datasets While Retaining Facial Expressions
Augmented probability simulation for adversarial risk analysis in general security games
Deep Learning From Trajectory Data: a Review of Neural Networks and the Trajectory Data Representations to Train Them.
Predictability and Comprehensibility in Post-Hoc XAI Methods: A User-Centered Analysis.
A ’glocal’ approach for real-time emergency event detection in Twitter
Impact Estimation of Emergency Events Using Social Media Streams
Zero-Shot Taxonomy Mapping for Document Classification
Advanced insights through systematic analysis: Mapping future research directions and opportunities for xAI in deep learning and artificial intelligence used in cybersecurity
Some statistical challenges in automated driving systems
Manipulating hidden-Markov-model inferences by corrupting batch data
Adversarial Machine Learning: Bayesian Perspectives
Domain-Aligned Data Augmentation for Low-Resource and Imbalanced Text Classification
Trend Detection in Crime-related Time Series with Change Point Detection Methods
One-shot logo detection for large video datasets and live camera surveillance in criminal investigations
Leveraging Continuous Learning for Fighting Misinformation
Geo-temporal crime forecasting using a Deep Learning attention-based model
Wider or Deeper Neural Network Architecture for Acoustic Scene Classification with Mismatched Recording Devices
Improved Likelihood Ratios for Surveillance Video Face Recognition with Multimodal Feature Pairing
Selective Word Substitution for Contextualized Data Augmentation 
Federated tool for anonymization and annotation in image data 
Context-Aware Feature Vectors in Dark Web Page Classification

Dissemination Materials

Project poster
Project leaflet