Detection Based Defense Against Adversarial Examples From the Steganalysis Point of View
Authors:
- 1 June 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 4820-4829
Abstract
Deep Neural Networks (DNNs) have recently led to significant improvements in many fields. However, DNNs are vulnerable to adversarial examples which are samples with imperceptible perturbations while dramatically misleading the DNNs. Moreover, adversarial examples can be used to perform an attack on various kinds of DNN based systems, even if the adversary has no access to the underlying model. Many defense methods have been proposed, such as obfuscating gradients of the networks or detecting adversarial examples. However it is proved out that these defense methods are not effective or cannot resist secondary adversarial attacks. In this paper, we point out that steganalysis can be applied to adversarial examples detection, and propose a method to enhance steganalysis features by estimating the probability of modifications caused by adversarial attacks. Experimental results show that the proposed method can accurately detect adversarial examples. Moreover, secondary adversarial attacks are hard to be directly performed to our method because our method is not based on a neural network but based on high-dimensional artificial features and Fisher Linear Discriminant ensemble.Keywords
All Related Versions
This publication has 15 references indexed in Scilit:
- Practical Black-Box Attacks against Machine Learning2017
- Deep Residual Learning for Image Recognition2016
- Distillation as a Defense to Adversarial Perturbations Against Deep Neural Networks2016
- The Limitations of Deep Learning in Adversarial Settings2016
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Selection-channel-aware rich model for Steganalysis of digital images2014
- Rich Models for Steganalysis of Digital ImagesIEEE Transactions on Information Forensics and Security, 2012
- Steganalysis by Subtractive Pixel Adjacency MatrixIEEE Transactions on Information Forensics and Security, 2010
- Steganalysis of spread spectrum data hiding exploiting cover memory2005
- Bagging predictorsMachine Learning, 1996