SSCNets: Robustifying DNNs using Secure Selective Convolutional Filters

Authors: Hassan Ali, Faiq Khalid, Hammad Tariq, Muhammad Abdullah Hanif, Semeen Rehman, Rehan Ahmed, Muhammad Shafique
Published: 2018-11-04 | Updated: 2020-05-15

Source: https://arxiv.org/abs/1811.01443

PDF: https://arxiv.org/pdf/1811.01443

AIにより推定されたラベル

ロバスト性向上 トリガーの検知 攻撃の評価

※ こちらのラベルはAIによって自動的に追加されました。そのため、正確でないことがあります。
詳細は文献データベースについてをご覧ください。

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.