3 papers
cs.LG2021
Analysis of Dominant Classes in Universal Adversarial Perturbations
Jon Vadillo, Roberto Santana, Jose A. Lozano
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 effici…
eess.AS2020
On the human evaluation of audio adversarial examples
Jon Vadillo, Roberto Santana
Human-machine interaction is increasingly dependent on speech communication. Machine Learning models are usually applied to interpret human speech commands. However, these models c…
cs.LG2019
Universal adversarial examples in speech command classification
Jon Vadillo, Roberto Santana
Adversarial examples are inputs intentionally perturbed with the aim of forcing a machine learning model to produce a wrong prediction, while the changes are not easily detectable…