Learning Transferable Adversarial Examples via Ghost Networks
arXiv: Computer Vision and Pattern Recognition, Volume abs/1812.03413, 2018.
Recent development of adversarial attacks has proven that ensemble-based methods outperform traditional, non-ensemble ones in black-box attack. However, these methods generally require a family of diverse models, and ensembling them together afterward, both of which are computationally expensive. In this paper, we propose Ghost Networks t...More
PPT (Upload PPT)