Compressive imaging for defending deep neural networks from adversarial attacks

被引：8

作者：

Kravets, Vladislav ^{[1
]}

Javidi, Bahram ^{[2
]}

Stern, Adrian ^{[1
]}

机构：

[1] Ben Gurion Univ Negev, Sch Elect & Comp Engn, Dept Electroopt & Photon Engn, POB 653, IL-8410501 Beer Sheva, Israel

[2] Univ Connecticut, Dept Elect & Comp Engn, U-4157, Storrs, CT 06269 USA

来源：

OPTICS LETTERS | 2021年 / 46卷 / 08期

关键词：

D O I：

10.1364/OL.418808

中图分类号：

O43 [光学];

学科分类号：

070207 ; 0803 ;

摘要：

Despite their outstanding performance, convolutional deep neural networks (DNNs) are vulnerable to small adversarial perturbations. In this Letter, we introduce a novel approach to thwart adversarial attacks. We propose to employ compressive sensing (CS) to defend DNNs from adversarial attacks, and at the same time to encode the image, thus preventing counterattacks. We present computer simulations and optical experimental results of object classification in adversarial images captured with a CS single pixel camera. (C) 2021 Optical Society of America

引用

页码：1951 / 1954

页数：4

共 50 条

[1] Defending Against Adversarial Attacks in Deep Neural Networks
You, Suya
Kuo, C-C Jay
[J]. ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING FOR MULTI-DOMAIN OPERATIONS APPLICATIONS, 2019, 11006
[2] Efficacy of Defending Deep Neural Networks against Adversarial Attacks with Randomization
Zhou, Yan
Kantarcioglu, Murat
Xi, Bowei
[J]. ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING FOR MULTI-DOMAIN OPERATIONS APPLICATIONS II, 2020, 11413
[3] GNNGUARD: Defending Graph Neural Networks against Adversarial Attacks
Zhang, Xiang
Zitnik, Marinka
[J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 33, NEURIPS 2020, 2020, 33
[4] HeteroGuard: Defending Heterogeneous Graph Neural Networks against Adversarial Attacks
Kumarasinghe, Udesh
Nabeel, Mohamed
De Zoysa, Kasun
Gunawardana, Kasun
Elvitigala, Charitha
[J]. 2022 IEEE INTERNATIONAL CONFERENCE ON DATA MINING WORKSHOPS, ICDMW, 2022, : 698 - 705
[5] Detecting adversarial example attacks to deep neural networks
Carrara, Fabio
Falchi, Fabrizio
Caldelli, Roberto
Amato, Giuseppe
Fumarola, Roberta
Becarelli, Rudy
[J]. PROCEEDINGS OF THE 15TH INTERNATIONAL WORKSHOP ON CONTENT-BASED MULTIMEDIA INDEXING (CBMI), 2017,
[6] Defending Quantum Neural Networks against Adversarial Attacks with Homomorphic Data Encryption
Wang, Ellen
Chain, Helena
Wang, Xiaodi
Ray, Avi
Wooldridge, Tyler
[J]. 2023 INTERNATIONAL CONFERENCE ON COMPUTATIONAL SCIENCE AND COMPUTATIONAL INTELLIGENCE, CSCI 2023, 2023, : 816 - 822
[7] Defending against adversarial attacks on graph neural networks via similarity property
Yao, Minghong
Yu, Haizheng
Bian, Hong
[J]. AI COMMUNICATIONS, 2023, 36 (01) : 27 - 39
[8] Recurrent Generative Adversarial Neural Networks for Compressive Imaging
Mardani, Morteza
Gong, Enhao
Cheng, Joseph Y.
Pauly, John
Xing, Lei
[J]. 2017 IEEE 7TH INTERNATIONAL WORKSHOP ON COMPUTATIONAL ADVANCES IN MULTI-SENSOR ADAPTIVE PROCESSING (CAMSAP), 2017,
[9] Neuron Selecting: Defending Against Adversarial Examples in Deep Neural Networks
Zhang, Ming
Li, Hu
Kuang, Xiaohui
Pang, Ling
Wu, Zhendong
[J]. INFORMATION AND COMMUNICATIONS SECURITY (ICICS 2019), 2020, 11999 : 613 - 629
[10] Defending Deep Learning Models Against Adversarial Attacks
Mani, Nag
Moh, Melody
Moh, Teng-Sheng
[J]. INTERNATIONAL JOURNAL OF SOFTWARE SCIENCE AND COMPUTATIONAL INTELLIGENCE-IJSSCI, 2021, 13 (01): : 72 - 89

← 1 2 3 4 5 →