TY - GEN
T1 - Compressive Sensing Methods for Defending Deep Learning 3D Classifiers
AU - Kravets, Vladislav
AU - Javidi, Bahram
AU - Stern, Adrian
N1 - Funding Information:
B. Javidi acknowledges support under Air Force Office of Scientific Research (FA9550-18-1-0338, FA9550-21-1-0333); Office of Naval Research (N000141712405, N00014-17-1-2561, N00014-20-1-2690).
Publisher Copyright:
© 2022 The Author(s)
PY - 2022/1/1
Y1 - 2022/1/1
N2 - We overview methods for defending deep learning algorithms from adversarial attacks by compressive 3D sensing. With optical compressive sensing, these methods exhibit outstanding robustness to adaptive attacks.
AB - We overview methods for defending deep learning algorithms from adversarial attacks by compressive 3D sensing. With optical compressive sensing, these methods exhibit outstanding robustness to adaptive attacks.
UR - http://www.scopus.com/inward/record.url?scp=85139133005&partnerID=8YFLogxK
U2 - https://doi.org/10.1364/3D.2022.3F3A.2
DO - https://doi.org/10.1364/3D.2022.3F3A.2
M3 - Conference contribution
AN - SCOPUS:85139133005
T3 - Optics InfoBase Conference Papers
BT - 3D Image Acquisition and Display
PB - Optica Publishing Group (formerly OSA)
T2 - 3D Image Acquisition and Display: Technology, Perception and Applications, 3D 2022
Y2 - 11 July 2022 through 15 July 2022
ER -