Characterizing Adversarial Samples of Convolutional Neural Networks

被引：0

作者：

Jiang, Cheng ^{[1
]}

Zhao, Qiyang ^{[1
]}

Liu, Yuzhong ^{[2
]}

机构：

[1] Beihang Univ, NLSDE, Beijing, Peoples R China

[2] Tech Infrastruct Grp JD, Beijing, Peoples R China

来源：

2018 11TH INTERNATIONAL CONGRESS ON IMAGE AND SIGNAL PROCESSING, BIOMEDICAL ENGINEERING AND INFORMATICS (CISP-BMEI 2018) | 2018年

关键词：

D O I：

暂无

中图分类号：

R318 [生物医学工程];

学科分类号：

0831 ;

摘要：

Adversarial samples aim to make deep convolutional neural networks predict incorrectly under small perturbations. This paper investigates non-targeted adversarial samples of convolutional neural networks and makes a primitive attempt to characterize adversarial samples. Two observations are made: first, adversarial perturbations are mainly in the high-frequency domain; second, adversarial categories usually have strong semantic relevance to the original categories. Our two observations provide a solid basis to understand the behavior of convolutional neural networks and thus to improve their robustness against adversarial samples.

引用

页数：6

共 50 条

[31] Robust convolutional neural networks against adversarial attacks on medical images
Shi, Xiaoshuang
Peng, Yifan
Chen, Qingyu
Keenan, Tiarnan
Thavikulwat, Alisa T.
Lee, Sungwon
Tang, Yuxing
Chew, Emily Y.
Summers, Ronald M.
Lu, Zhiyong
PATTERN RECOGNITION, 2022, 132
[32] Sanitizing hidden activations for improving adversarial robustness of convolutional neural networks
Mu, Tianshi
Lin, Kequan
Zhang, Huabing
Wang, Jian
JOURNAL OF INTELLIGENT & FUZZY SYSTEMS, 2021, 41 (02) : 3993 - 4003
[33] Seismic facies classification using supervised convolutional neural networks and semisupervised generative adversarial networks
Liu, Mingliang
Jervis, Michael
Li, Weichang
Nivlet, Philippe
GEOPHYSICS, 2020, 85 (04) : O47 - O58
[34] Using Generative Adversarial Networks and Parameter Optimization of Convolutional Neural Networks for Lung Tumor Classification
Lin, Chun-Hui
Lin, Cheng-Jian
Li, Yu-Chi
Wang, Shyh-Hau
APPLIED SCIENCES-BASEL, 2021, 11 (02): : 1 - 17
[35] Using Generative Adversarial Networks and Transfer Learning for Breast Cancer Detection by Convolutional Neural Networks
Guan, Shuyue
Loew, Murray
MEDICAL IMAGING 2019: IMAGING INFORMATICS FOR HEALTHCARE, RESEARCH, AND APPLICATIONS, 2019, 10954
[36] Hierarchical binding in convolutional neural networks: Making adversarial attacks geometrically challenging
Leadholm, Niels
Stringer, Simon
NEURAL NETWORKS, 2022, 155 : 258 - 286
[37] Adversarial attacks on spiking convolutional neural networks for event-based vision
Buechel, Julian
Lenz, Gregor
Hu, Yalun
Sheik, Sadique
Sorbaro, Martino
FRONTIERS IN NEUROSCIENCE, 2022, 16
[38] Salient Object Detection Using Cascaded Convolutional Neural Networks and Adversarial Learning
Tang, Youbao
Wu, Xiangqian
IEEE TRANSACTIONS ON MULTIMEDIA, 2019, 21 (09) : 2237 - 2247
[39] Vulnerable point detection and repair against adversarial attacks for convolutional neural networks
Jie Gao
Zhaoqiang Xia
Jing Dai
Chen Dang
Xiaoyue Jiang
Xiaoyi Feng
International Journal of Machine Learning and Cybernetics, 2023, 14 : 4163 - 4192
[40] Audio Steganography Based on Iterative Adversarial Attacks Against Convolutional Neural Networks
Wu, Junqi
Chen, Bolin
Luo, Weiqi
Fang, Yanmei
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2020, 15 : 2282 - 2294

← 1 2 3 4 5 →