Uncertainty as a Swiss army knife: new adversarial attack and defense ideas based on epistemic uncertainty
Open Access
- 2 April 2022
- journal article
- research article
- Published by Springer Nature in Complex & Intelligent Systems
- Vol. 9 (4) , 3739-3757
Abstract
Although state-of-the-art deep neural network models are known to be robust to random perturbations, it was verified that these architectures are indeed quite vulnerable to deliberately crafted perturbations, albeit being quasi-imperceptible. These vulnerabilities make it challenging to deploy deep neural network models in the areas where security is a critical concern. In recent years, many research studies have been conducted to develop new attack methods and come up with new defense techniques that enable more robust and reliable models. In this study, we use the quantified epistemic uncertainty obtained from the model’s final probability outputs, along with the model’s own loss function, to generate more effective adversarial samples. And we propose a novel defense approach against attacks like Deepfool which result in adversarial samples located near the model’s decision boundary. We have verified the effectiveness of our attack method on MNIST (Digit), MNIST (Fashion) and CIFAR-10 datasets. In our experiments, we showed that our proposed uncertainty-based reversal method achieved a worst case success rate of around 95% without compromising clean accuracy.Keywords
This publication has 35 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
- Deep Residual Learning for Image Recognition2016
- You Only Look Once: Unified, Real-Time Object Detection2016
- Distillation as a Defense to Adversarial Perturbations Against Deep Neural Networks2016
- The Go Files: AI computer wraps up 4-1 victory against human championNature, 2016
- Effective Approaches to Attention-based Neural Machine Translation2015
- Reliable classification: Learning classifiers that distinguish aleatoric and epistemic uncertaintyInformation Sciences, 2014
- Approximation by superpositions of a sigmoidal functionMathematics of Control, Signals, and Systems, 1989