On the Robustness to Adversarial Examples of Neural ODE Image Classifiers
- 1 December 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Abstract
The vulnerability of deep neural networks to adversarial attacks currently represents one of the most challenging open problems in the deep learning field. The NeurIPS 2018 work that obtained the best paper award proposed a new paradigm for defining deep neural networks with continuous internal activations. In this kind of networks, dubbed Neural ODE Networks, a continuous hidden state can be defined via parametric ordinary differential equations, and its dynamics can be adjusted to build representations for a given task, such as image classification. In this paper, we analyze the robustness of image classifiers implemented as ODE Nets to adversarial attacks and compare it to standard deep models. We show that Neural ODE are natively more robust to adversarial attacks with respect to state-of-the-art residual networks, and some of their intrinsic properties, such as adaptive computation cost, open new directions to further increase the robustness of deep-learned models. Moreover, thanks to the continuity of the hidden state, we are able to follow the perturbation injected by manipulated inputs and pinpoint the part of the internal dynamics that is most responsible for the misclassification.Keywords
This publication has 14 references indexed in Scilit:
- Adversarial image detection in deep neural networksMultimedia Tools and Applications, 2018
- Adversarial Examples Detection in Deep Networks with Convolutional Filter Statistics2017
- Towards Evaluating the Robustness of Neural Networks2017
- Exploring the space of adversarial images2016
- Distillation as a Defense to Adversarial Perturbations Against Deep Neural Networks2016
- The Limitations of Deep Learning in Adversarial Settings2016
- Evasion Attacks against Machine Learning at Test Time2013
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Solving Ordinary Differential Equations II1991
- A family of embedded Runge-Kutta formulaeJournal of Computational and Applied Mathematics, 1980