Adversarial training (AT) is one of the most effective defenses against adversarial attacks for
deep learning models. In this work, we advocate incorporating the hypersphere embedding …

Data Poisoning Attacks (DPA) represent a sophisticated technique aimed at distorting the
training data of machine learning models, thereby manipulating their behavior. This process …

Despite the large success of deep neural networks (DNN) in recent years, most neural
networks still lack mathematical guarantees in terms of stability. For instance, DNNs are …

Adversarial examples are usually generated by adding adversarial perturbations on clean
samples, designed to deceive the model to make wrong classifications. Adversarial …

This research is in threat analysis and countermeasures employing Artificial Intelligence (AI)
methods within the civilian domain, where safety and mission-critical aspects are essential …

A repeatable and deterministic non-random weight initialization method in convolutional
layers of neural networks examined with the Fast Gradient Sign Method (FSGM). Using the …

In this paper we explore some of the potential applications of robustness criteria for machine
learning (ML) systems by way of tangible “demonstrator” scenarios. In each demonstrator …

Deep neural networks are widely used in signal processing from a broad range of areas due
to their good performances, including computer vision, natural language processing …