Compressive imaging for defending deep neural networks from adversarial attacks
Abstract
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.
Document Details
- Document Type
- Pub Defense Publication
- Publication Date
- Apr 15, 2021
- Source ID
- 10.1364/ol.418808
Entities
People
- Adrian Stern
- Bahram Javidi
- Vladislav Kravets
Organizations
- Air Force Office of Scientific Research
- Ben-Gurion University of the Negev
- Office of Naval Research
- University of Connecticut