Exploiting epistemic uncertainty of the deep learning models to generate adversarial samples
- 18 February 2022
- journal article
- research article
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 81 (8) , 11479-11500
Abstract
Deep neural network (DNN) architectures are considered to be robust to random perturbations. Nevertheless, it was shown that they could be severely vulnerable to slight but carefully crafted perturbations of the input, termed as adversarial samples. In recent years, numerous studies have been conducted in this new area called ``Adversarial Machine Learning” to devise new adversarial attacks and to defend against these attacks with more robust DNN architectures. However, most of the current research has concentrated on utilising model loss function to craft adversarial examples or to create robust models. This study explores the usage of quantified epistemic uncertainty obtained from Monte-Carlo Dropout Sampling for adversarial attack purposes by which we perturb the input to the shifted-domain regions where the model has not been trained on. We proposed new attack ideas by exploiting the difficulty of the target model to discriminate between samples drawn from original and shifted versions of the training data distribution by utilizing epistemic uncertainty of the model. Our results show that our proposed hybrid attack approach increases the attack success rates from 82.59% to 85.14%, 82.96% to 90.13% and 89.44% to 91.06% on MNIST Digit, MNIST Fashion and CIFAR-10 datasets, respectively.Keywords
All Related Versions
This publication has 32 references indexed in Scilit:
- Towards Evaluating the Robustness of Neural Networks2017
- Practical Black-Box Attacks against Machine Learning2017
- DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks2016
- Separable data hiding in encrypted image based on compressive sensing and discrete fourier transformMultimedia Tools and Applications, 2016
- Deep Residual Learning for Image Recognition2016
- The Go Files: AI computer wraps up 4-1 victory against human championNature, 2016
- Reliable classification: Learning classifiers that distinguish aleatoric and epistemic uncertaintyInformation Sciences, 2014
- Bayesian Learning for Neural Networks1996
- Training a 3-node neural network is NP-completeNeural Networks, 1992
- Approximation by superpositions of a sigmoidal functionMathematics of Control, Signals, and Systems, 1989