TY - JOUR
T1 - Defending deep neural networks from adversarial attacks on three-dimensional images by compressive sensing
AU - Kravets, Vladislav
AU - Javidi, Bahram
AU - Stern, Adrian
N1 - Funding Information:
B. Javidi acknowledges support by The Office of Naval Research (N00014-17-1-2561, N000141712405, N00014-20-1-2690), and The Air Force Office of Scientific Research (FA9550-18-1-0338).
Publisher Copyright:
© 2021 The Author(s)
PY - 2021/1/1
Y1 - 2021/1/1
N2 - We demonstrate the utility of compressive sensing to defend against adversarial attacks on deep learning classifiers and to encrypt the 3D image, thus, to avoid counterattacks.
AB - We demonstrate the utility of compressive sensing to defend against adversarial attacks on deep learning classifiers and to encrypt the 3D image, thus, to avoid counterattacks.
UR - http://www.scopus.com/inward/record.url?scp=85166463831&partnerID=8YFLogxK
U2 - 10.1364/3D.2021.3Tu1C.1
DO - 10.1364/3D.2021.3Tu1C.1
M3 - Conference article
AN - SCOPUS:85166463831
SN - 2162-2701
JO - Optics InfoBase Conference Papers
JF - Optics InfoBase Conference Papers
T2 - 3D Image Acquisition and Display: Technology, Perception and Applications, 3D 2021 - Part of Imaging and Applied Optics Congress 2021
Y2 - 19 July 2021 through 23 July 2021
ER -