Defense against adversarial attacks on deep convolutional neural networks through nonlocal denoising
arXiv:2206.12685 · doi:10.11591/ijai.v11.i3.pp961-968
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% in the CIFAR-10 data set. Training using 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.
References in corpus (11)
- Explaining and Harnessing Adversarial Examples
- Intriguing properties of neural networks
- BAE: BERT-based Adversarial Examples for Text Classification
- Robust Physical-World Attacks on Deep Learning Models
- Deep Text Classification Can be Fooled
- Transfer Learning using CNN for Handwritten Devanagari Character Recognition
- Why Do Adversarial Attacks Transfer? Explaining Transferability of Evasion and Poisoning Attacks
- Robustness of Bayesian Neural Networks to Gradient-Based Attacks
- Divide, Denoise, and Defend against Adversarial Attacks
- Semi-Supervised Learning for Cancer Detection of Lymph Node Metastases
- Model-Centric and Data-Centric Aspects of Active Learning for Deep Neural Networks