Leveraging Image Processing Techniques to Thwart Adversarial Attacks in Image Classification
2019 IEEE International Symposium on Multimedia (ISM)
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.
Locate the Document
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.