Boosting Targeted Black-Box Attacks via Ensemble Substitute Training and Linear Augmentation

These years, Deep Neural Networks (DNNs) have shown unprecedented performance in many areas. However, some recent studies revealed their vulnerability to small perturbations added on source inputs. Furthermore, we call the ways to generate these perturbations’ adversarial attacks, which contain two...

Full description

Bibliographic Details
Main Authors: Xianfeng Gao, Yu-an Tan, Hongwei Jiang, Quanxin Zhang, Xiaohui Kuang
Format: Article
Language:English
Published: MDPI AG 2019-06-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/9/11/2286