Leveraging Image Processing Techniques to Thwart Adversarial Attacks in Image Classification

Authors

Yeganeh Jalalpour, Portland State UniversityFollow
Li-Yun Wang, Portland State UniversityFollow
Ryan Feng, Portland State UniversityFollow
Wu-chi Feng, Portland State UniversityFollow

Published In

2019 IEEE International Symposium on Multimedia (ISM)

Document Type

Citation

Publication Date

1-2020

Abstract

Deep Convolutional Neural Networks (DCNNs) are vulnerable to images that have been altered with well-engineered and imperceptible perturbations. We propose three color quantization pre-processing techniques to make DCNNs more robust to adversarial perturbation including Gaussian smoothing and PNM color reduction (GPCR), color quantization using Gaussian smoothing and K-means (GK-means), and fast GK-means. We evaluate the approaches on a subset of the ImageNet dataset. Our evaluation reveals that our GK-means-based algorithms have the best top-1 accuracy. We also present the trade-off between GK-means-based algorithms and GPCR with respect to computational time.

Description

© Copyright 2020 IEEE

Locate the Document

http://doi.org/10.1109/ISM46123.2019.00040

DOI

10.1109/ISM46123.2019.00040

Persistent Identifier

https://archives.pdx.edu/ds/psu/33400

Citation Details

Y. Jalalpour, L. Wang, R. Feng and W. Feng, "Leveraging Image Processing Techniques to Thwart Adversarial Attacks in Image Classification," 2019 IEEE International Symposium on Multimedia (ISM), San Diego, CA, USA, 2019, pp. 184-1847, doi: 10.1109/ISM46123.2019.00040.