Decoupling direction and norm for efficient gradient-based l2 adversarial attacks
Decoupling direction and norm for efficient gradient-based l2 adversarial attacks
Rony, Jérôme, Gustavo, Luiz, Sabourin, Robert and Granger, Eric.
In NeurIPS 2018 Workshop on Security in Machine Learning (Montreal, QC, Canada, Dec. 7, 2018) 2018