Ensemble Methods as a Defense to Adversarial Perturbations Against Deep Neural Networks
This addresses safety concerns in applications like self-driving cars, but it is an incremental approach building on existing ensemble techniques.
The paper tackles the vulnerability of deep neural networks to adversarial perturbations, proposing ensemble methods as a defense strategy, and empirically shows that ensembles improve accuracy and robustness on MNIST and CIFAR-10 datasets.
Deep learning has become the state of the art approach in many machine learning problems such as classification. It has recently been shown that deep learning is highly vulnerable to adversarial perturbations. Taking the camera systems of self-driving cars as an example, small adversarial perturbations can cause the system to make errors in important tasks, such as classifying traffic signs or detecting pedestrians. Hence, in order to use deep learning without safety concerns a proper defense strategy is required. We propose to use ensemble methods as a defense strategy against adversarial perturbations. We find that an attack leading one model to misclassify does not imply the same for other networks performing the same task. This makes ensemble methods an attractive defense strategy against adversarial attacks. We empirically show for the MNIST and the CIFAR-10 data sets that ensemble methods not only improve the accuracy of neural networks on test data but also increase their robustness against adversarial perturbations.