Towards Robust Neural Networks via Random Self-ensemble
Xuanqing Liu
and
Minhao Cheng
and
Huan Zhang
and
Cho-Jui Hsieh
arXiv e-Print archive - 2017 via arXiv
Keywords:
cs.LG, cs.CR, stat.ML
First published: 2017/12/02 (6 years ago) Abstract: Recent studies have revealed the vulnerability of deep neural networks: A
small adversarial perturbation that is imperceptible to human can easily make a
well-trained deep neural network misclassify. This makes it unsafe to apply
neural networks in security-critical applications. In this paper, we propose a
new defense algorithm called Random Self-Ensemble (RSE) by combining two
important concepts: {\bf randomness} and {\bf ensemble}. To protect a targeted
model, RSE adds random noise layers to the neural network to prevent the strong
gradient-based attacks, and ensembles the prediction over random noises to
stabilize the performance. We show that our algorithm is equivalent to ensemble
an infinite number of noisy models $f_\epsilon$ without any additional memory
overhead, and the proposed training procedure based on noisy stochastic
gradient descent can ensure the ensemble model has a good predictive
capability. Our algorithm significantly outperforms previous defense techniques
on real data sets. For instance, on CIFAR-10 with VGG network (which has 92\%
accuracy without any attack), under the strong C\&W attack within a certain
distortion tolerance, the accuracy of unprotected model drops to less than
10\%, the best previous defense technique has $48\%$ accuracy, while our method
still has $86\%$ prediction accuracy under the same level of attack. Finally,
our method is simple and easy to integrate into any neural network.
Liu et al. propose randomizing neural networks, implicitly learning an ensemble of models, to defend against adversarial attacks. In particular, they introduce Gaussian noise layers before regular convolutional layers. The noise can be seen as additional parameter of the model. During training, noise is randomly added. During testing, the model is evaluated on a single testing input using multiple random noise vectors; this essentially corresponds to an ensemble of different models (parameterized by the different noise vectors).
Mathemtically, the authors provide two interesting interpretations. First, they argue that training essentially minimizes an upper bound of the (noisy) inference loss. Second, they show that their approach is equivalent to Lipschitz regularization [1].
[1] M. Hein, M. Andriushchenko. Formal guarantees on the robustness of a classifier against adversarial manipulation. ArXiv:1705.08475, 2017.
Also view this summary at [davidstutz.de](https://davidstutz.de/category/reading/).