Understanding and Improving
Fast Adversarial Training
Maksym Andriushchenko Nicolas Flammarion
EPFL, Theory of Machine Learning Lab EPFL, Theory of Machine Learning Lab
maksym.andriushchenko@epfl.ch nicolas.flammarion@epfl.ch
Abstract
A recent line of work focused on making adversarial training computationally
efficient for deep learning models. In particular, Wong et al. [47] showed that
`∞ -adve ...


雷达卡


京公网安备 11010802022788号







