Effects of Image Processing Operations on Adversarial Noise and Their Use in Detecting and Correcting Adversarial Images
- 1 January 2022
- journal article
- research article
- Published by Institute of Electronics, Information and Communications Engineers (IEICE) in IEICE Transactions on Information and Systems
- Vol. E105.D (1), 65-77
- https://doi.org/10.1587/transinf.2021mup0005
Abstract
Deep neural networks (DNNs) have achieved excellent performance on several tasks and have been widely applied in both academia and industry. However, DNNs are vulnerable to adversarial machine learning attacks in which noise is added to the input to change the networks' output. Consequently, DNN-based mission-critical applications such as those used in self-driving vehicles have reduced reliability and could cause severe accidents and damage. Moreover, adversarial examples could be used to poison DNN training data, resulting in corruptions of trained models. Besides the need for detecting adversarial examples, correcting them is important for restoring data and system functionality to normal. We have developed methods for detecting and correcting adversarial images that use multiple image processing operations with multiple parameter values. For detection, we devised a statistical-based method that outperforms the feature squeezing method. For correction, we devised a method that uses for the first time two levels of correction. The first level is label correction, with the focus on restoring the adversarial images' original predicted labels (for use in the current task). The second level is image correction, with the focus on both the correctness and quality of the corrected images (for use in the current and other tasks). Our experiments demonstrated that the correction method could correct nearly 90% of the adversarial images created by classical adversarial attacks and affected only about 2% of the normal images.Keywords
This publication has 25 references indexed in Scilit:
- Xception: Deep Learning with Depthwise Separable ConvolutionsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2017
- Universal Adversarial PerturbationsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2017
- Towards Evaluating the Robustness of Neural NetworksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2017
- DeepFool: A Simple and Accurate Method to Fool Deep Neural NetworksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- Deep Residual Learning for Image RecognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- Distillation as a Defense to Adversarial Perturbations Against Deep Neural NetworksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- The Limitations of Deep Learning in Adversarial SettingsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Support-vector networksMachine Learning, 1995
- The multilayer perceptron as an approximation to a Bayes optimal discriminant functionIEEE Transactions on Neural Networks, 1990