Adversarial Risk and the Dangers of Evaluating Against Weak Attacks
This paper investigates recently proposed approaches for defending against adversarial examples and evaluating adversarial robustness. We motivate
3 accepted papers
This paper investigates recently proposed approaches for defending against adversarial examples and evaluating adversarial robustness. We motivate
Sequential models achieve state-of-the-art results in audio, visual and textual domains with respect to both estimating the data distribution and generating desired samples. Efficient sampling for this class of models at the cost of little to no loss in quality has however remained an elusive proble…
The recently-developed WaveNet architecture is the current state of the art in realistic speech synthesis, consistently rated as more natural sounding for many different languages than any previous system. However, because WaveNet relies on sequential generation of one audio sample at a time, it is…