In this paper, we introduce a novel technique based on the Secure Selective Convolutional (SSC) techniques in the training loop that increases the robustness of a given DNN by allowing it to learn the data distribution based on the important edges in the input image. We validate our technique on Convolutional DNNs against the state-of-the-art attacks from the open-source Cleverhans library using the MNIST, the CIFAR-10, and the CIFAR-100 datasets. Our experimental results show that the attack success rate, as well as the imperceptibility of the adversarial images, can be significantly reduced by adding effective pre-processing functions, i.e., Sobel filtering.
@article{arxiv.1811.01443,
title = {SSCNets: Robustifying DNNs using Secure Selective Convolutional Filters},
author = {Hassan Ali and Faiq Khalid and Hammad Tariq and Muhammad Abdullah Hanif and Semeen Rehman and Rehan Ahmed and Muhammad Shafique},
journal= {arXiv preprint arXiv:1811.01443},
year = {2020}
}