Universal Adversarial TrainingUniversal Adversarial TrainingShafahi, Ali and Najibi, Mahyar and Xu, Zheng and Dickerson, John P. and Davis, Larry S. and Goldstein, Tom2018
Paper summarydavidstutzShafahi et al. propose universal adversarial training, meaning training on universal adversarial examples. In contrast to regular adversarial examples, universal ones represent perturbations that cause a network to mis-classify many test images. In contrast to regular adversarial training, where several additional iterations are required on each batch of images, universal adversarial training only needs one additional forward/backward pass on each batch. The obtained perturbations for each batch are accumulated in a universal adversarial examples. This makes adversarial training more efficient, however reduces robustness significantly.
Also find this summary at [davidstutz.de](https://davidstutz.de/category/reading/).
Universal Adversarial Training
Dickerson, John P.
Davis, Larry S.
arXiv e-Print archive - 2018 via Local Bibsonomy