ROBUSTNESS OF DEEP NEURAL NETWORKS IN ADVERSARIAL EXAMPLES

被引：0

作者：

Teng, Da ^{[1
]}

Song, Xiao m ^{[1
]}

Gong, Guanghong ^{[1
]}

Han, Liang ^{[1
]}

机构：

[1] Beihang Univ, Sch Automat, Beijing, Peoples R China

来源：

INTERNATIONAL JOURNAL OF INDUSTRIAL ENGINEERING-THEORY APPLICATIONS AND PRACTICE | 2017年 / 24卷 / 02期

关键词：

machine learning; deep learning; neural networks; adversarial examples; COMMAND;

D O I：

暂无

中图分类号：

T [工业技术];

学科分类号：

08 ;

摘要：

Deep neural networks have achieved state-of-the-art performance in many artificial intelligence areas, such as object recognition, speech recognition, and machine translation. While deep neural networks have high expression capabilities, they are prone to over fitting due to the high dimensionalities of the networks. In recent applications, deep neural networks have been found to be unstable in adversarial perturbations, which are small but can increase the network's prediction errors. This paper proposes a novel training algorithm to improve the robustness of the neural networks in adversarial examples.

引用

页码：123 / 133

页数：11

共 50 条

[21] A decade of adversarial examples: a survey on the nature and understanding of neural network non-robustness
Trusov, A. V.
Limonova, E. E.
Arlazarov, V. V.
COMPUTER OPTICS, 2025, 49 (02) : 222 - 252
[22] Robustness to adversarial examples can be improved with overfitting
Deniz, Oscar
Pedraza, Anibal
Vallez, Noelia
Salido, Jesus
Bueno, Gloria
INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS, 2020, 11 (04) : 935 - 944
[23] Robustness to adversarial examples can be improved with overfitting
Oscar Deniz
Anibal Pedraza
Noelia Vallez
Jesus Salido
Gloria Bueno
International Journal of Machine Learning and Cybernetics, 2020, 11 : 935 - 944
[24] Deep Networks with RBF Layers to Prevent Adversarial Examples
Vidnerova, Petra
Neruda, Roman
ARTIFICIAL INTELLIGENCE AND SOFT COMPUTING, ICAISC 2018, PT I, 2018, 10841 : 257 - 266
[25] Generalizing universal adversarial perturbations for deep neural networks
Yanghao Zhang
Wenjie Ruan
Fu Wang
Xiaowei Huang
Machine Learning, 2023, 112 : 1597 - 1626
[26] Generalizing universal adversarial perturbations for deep neural networks
Zhang, Yanghao
Ruan, Wenjie
Wang, Fu
Huang, Xiaowei
MACHINE LEARNING, 2023, 112 (05) : 1597 - 1626
[27] ε-Weakened Robustness of Deep Neural Networks
Huang, Pei
Yang, Yuting
Liu, Minghao
Jia, Fuqi
Ma, Feifei
Zhang, Jian
PROCEEDINGS OF THE 31ST ACM SIGSOFT INTERNATIONAL SYMPOSIUM ON SOFTWARE TESTING AND ANALYSIS, ISSTA 2022, 2022, : 126 - 138
[28] Adversarial Minimax Training for Robustness Against Adversarial Examples
Komiyama, Ryota
Hattori, Motonobu
NEURAL INFORMATION PROCESSING (ICONIP 2018), PT II, 2018, 11302 : 690 - 699
[29] Effect of adversarial examples on the robustness of CAPTCHA
Zhang, Yang
Gao, Haichang
Pei, Ge
Kang, Shuai
Zhou, Xin
2018 INTERNATIONAL CONFERENCE ON CYBER-ENABLED DISTRIBUTED COMPUTING AND KNOWLEDGE DISCOVERY (CYBERC 2018), 2018, : 1 - 10
[30] Adversarial Robustness of Deep Learning: Theory, Algorithms, and Applications
Ruan, Wenjie
Yi, Xinping
Huang, Xiaowei
PROCEEDINGS OF THE 30TH ACM INTERNATIONAL CONFERENCE ON INFORMATION & KNOWLEDGE MANAGEMENT, CIKM 2021, 2021, : 4866 - 4869

← 1 2 3 4 5 →