Browsing Artículos by Author "Vadillo Jueguen, Jon"
Now showing items 1-2 of 2
-
Analysis of dominant classes in universal adversarial perturbations
The reasons why Deep Neural Networks are susceptible to being fooled by adversarial examples remains an open discussion. Indeed, many different strategies can be employed to efficiently generate adversarial attacks, some ... -
On the human evaluation of universal audio adversarial perturbations
[EN] Human-machine interaction is increasingly dependent on speech communication, mainly due to the remarkable performance of Machine Learning models in speech recognition tasks. However, these models can be fooled by ...