Defense against adversarial attacks on deep convolutional neural networks through nonlocal denoising

Authors: Sandhya Aneja, Nagender Aneja, Pg Emeroylariffion Abas, Abdul Ghani Naim
Published: 2022-06-25

Source: https://arxiv.org/abs/2206.12685

PDF: https://arxiv.org/pdf/2206.12685

AIにより推定されたラベル

敵対的攻撃手法 学習の改善 アルゴリズム設計

※ 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

Despite substantial advances in network architecture performance, the susceptibility of adversarial attacks makes deep learning challenging to implement in safety-critical applications. This paper proposes a data-centric approach to addressing this problem. A nonlocal denoising method with different luminance values has been used to generate adversarial examples from the Modified National Institute of Standards and Technology database (MNIST) and Canadian Institute for Advanced Research (CIFAR-10) data sets. Under perturbation, the method provided absolute accuracy improvements of up to 9.3 in the MNIST data set and 13 transformed images with higher luminance values increases the robustness of the classifier. We have shown that transfer learning is disadvantageous for adversarial machine learning. The results indicate that simple adversarial examples can improve resilience and make deep learning easier to apply in various applications.