4 papers
NERO-Net: A Neuroevolutionary Approach for the Design of Adversarially Robust CNNs
Inês Valentim, Nuno Antunes, Nuno Lourenço
Neuroevolution automates the complex task of neural network design but often ignores the inherent adversarial fragility of evolved models which is a barrier to adoption in safety-c…
Exploring Layerwise Adversarial Robustness Through the Lens of t-SNE
Inês Valentim, Nuno Antunes, Nuno Lourenço
Adversarial examples, designed to trick Artificial Neural Networks (ANNs) into producing wrong outputs, highlight vulnerabilities in these models. Exploring these weaknesses is cru…
Adversarial Robustness Assessment of NeuroEvolution Approaches
Inês Valentim, Nuno Lourenço, Nuno Antunes
NeuroEvolution automates the generation of Artificial Neural Networks through the application of techniques from Evolutionary Computation. The main goal of these approaches is to b…
The Impact of Data Preparation on the Fairness of Software Systems
Inês Valentim, Nuno Lourenço, Nuno Antunes
Machine learning models are widely adopted in scenarios that directly affect people. The development of software systems based on these models raises societal and legal concerns, a…