Paper Info
Title
Gradient Band-based Adversarial Training for Generalized Attack Immunity of A3C Path Finding.
Abstract
As adversarial attacks pose a serious threat to the security of AI system in practice, such attacks have been extensively studied in the context of computer vision applications. However, few attentions have been paid to the adversarial research on automatic path finding. In this paper, we show dominant adversarial examples are effective when targeting A3C path finding, and design a Common Dominant Adversarial Examples Generation Method (CDG) to generate dominant adversarial examples against any given map. In addition, we propose Gradient Band-based Adversarial Training, which trained with a single randomly choose dominant adversarial example without taking any modification, to realize the "1:N" attack immunity for generalized dominant adversarial examples. Extensive experimental results show that, the lowest generation precision for CDG algorithm is 91.91%, and the lowest immune precision for Gradient Band-based Adversarial Training is 93.89%, which can prove that our method can realize the generalized attack immunity of A3C path finding with a high confidence.
Year
Venue
Field
2018
arXiv: Learning
Artificial intelligence,Machine learning,Mathematics,Adversarial system
DocType
Volume
Citations 
Journal
abs/1807.06752
0
PageRank 
References 
Authors
0.34
0
7
Name
Order
Citations
PageRank
Tong Chen1229.69
Wenjia Niu217830.33
Yingxiao Xiang333.87
XiaoXuan Bai401.01
Jiqiang Liu531552.31
Zhen Han613321.19
Gang Li738162.77