@inproceedings{493567f0e27646f2b43779f7a53e9c35,
title = "Defense against Adversarial Attacks with an Induced Class",
abstract = "Though deep neural networks have succeeded in various real applications, the prediction performance is significantly degraded when facing adversarial attacks. In this work, we investigate the alternation of the prediction distribution pattern under adversarial attacks and argue that such alternation is the primary reason for performance drop. To this end, we propose a simple yet effective method by introducing an induced class to attract the adversarial attack and thus protect the original classes' prediction order. Experiments on two real-world datasets demonstrate that the proposed method can maintain the prediction performance for both natural and adversarial examples.",
keywords = "Adversarial Attack, Deep neural network, Defense",
author = "Zhi Xu and Jun Wang and Jian Pu",
note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 2021 International Joint Conference on Neural Networks, IJCNN 2021 ; Conference date: 18-07-2021 Through 22-07-2021",
year = "2021",
month = jul,
day = "18",
doi = "10.1109/IJCNN52387.2021.9533755",
language = "英语",
series = "Proceedings of the International Joint Conference on Neural Networks",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "IJCNN 2021 - International Joint Conference on Neural Networks, Proceedings",
address = "美国",
}