Convergence of Adversarial Training in Overparametrized Neural Networks

Ruiqi Gao, Tianle Cai, Haochuan Li, Cho-Jui Hsieh, Liwei Wang, Jason D. Lee

Neural Information Processing Systems 

Neural networks are vulnerable to adversarial examples, i.e. inputs that are imperceptibly perturbed from natural data and yet incorrectly classified by the network.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found