English

SSCNets: Robustifying DNNs using Secure Selective Convolutional Filters

Machine Learning 2020-05-18 v2 Cryptography and Security Machine Learning

Abstract

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.

Keywords

Cite

@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}
}
R2 v1 2026-06-23T05:03:40.139Z