Work

Dropping Pixels for Adversarial Robustness

Year: 2019

Type: conference-paper

Abstract: Deep neural networks are vulnerable against adversarial examples. In this paper, we propose to train and test the networks with randomly subsampled images with high drop rates. We show that this approach significantly improves robustness against adversarial examples in all cases of bounded L0, L2and L∞perturbations, while reducing the standard accuracy by a small value. We argue that subsampling pixels can be thought to provide a set of robust features for the input image and, thus, improves robustness without performing adversarial training.

Source: IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

DOI: 10.1109/cvprw.2019.00017

Authors: Hossein Hosseini, Sreeram Kannan, Radha Poovendran

Institution: University of Washington

Language: English

Topic: Adversarial Robustness in Machine Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: Office of Naval Research

Awards: G1390332038, G8876996369, G8929337198