SSCNets: Robustifying DNNs using Secure Selective Convolutional Filters
This addresses the problem of adversarial vulnerability in DNNs for computer vision applications, offering an incremental improvement through pre-processing techniques.
The paper tackles the problem of improving the robustness of deep neural networks against adversarial attacks by introducing Secure Selective Convolutional (SSC) techniques in training, which focus on learning from important edges in images. Results show significant reductions in attack success rates and imperceptibility of adversarial images on MNIST, CIFAR-10, and CIFAR-100 datasets using Sobel filtering.
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.