Add to BibSonomyAbstract
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.
© 2022 The Author(s)
PDF Article | Presentation VideoMore Like This
Defending deep neural networks from adversarial attacks on three-dimensional images by compressive sensing
Vladislav Kravets, Bahram Javidi, and Adrian Stern
3Tu1C.1 3D Image Acquisition and Display: Technology, Perception and Applications (3D) 2021
Optical firewall for defending deep neural networks from adversarial attacks
Vladislav Kravets, Bahram Javidi, and Adrian Stern
FW5A.2 Frontiers in Optics (FiO) 2021
Real-Time Reconstruction of 3D Compressive Samples with Deep Learning
Vladislav Kravets and Adrian Stern
3F2A.2 3D Image Acquisition and Display: Technology, Perception and Applications (3D) 2022