Manifold Regularized Deep Neural Networks using Adversarial Examples
Learning meaningful representations using deep neural networks involves designing efficient training schemes and well-structured networks. Currently, the method of stochastic gradient descent that has a momentum with dropout is one of the most popular training protocols. Based on that, more advanced methods (i.e., Maxout and Batch Normalization) have been proposed in recent years, but most still suffer from performance degradation caused by small perturbations, also known as adversarial examples. To address this issue, we propose manifold regularized networks (MRnet) that utilize a novel training objective function that minimizes the difference between multi-layer embedding results of samples and those adversarial. Our experimental results demonstrated that MRnet is more resilient to adversarial examples and helps us to generalize representations on manifolds. Furthermore, combining MRnet and dropout allowed us to achieve competitive classification performances for three well-known benchmarks: MNIST, CIFAR-10, and SVHN.
Code (0)
등록된 구현이 없습니다.
Tasks
General ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Towards Robustness of Deep Neural Networks via Regularization
Recent studies have demonstrated the vulnerability of deep neural networks against adversarial examples. Inspired by the observation that adversarial examples often lie outside the natural image data manifold and the…
Adversarial AttackAdversarial RobustnessUnderstanding Adversarial Robustness Against On-manifold Adversarial Examples
Deep neural networks (DNNs) are shown to be vulnerable to adversarial examples. A well-trained model can be easily attacked by adding small perturbations to the original data. One of the hypotheses of the existence of th…
Adversarial RobustnessGeneralized Loss-Sensitive Adversarial Learning with Manifold Margins
The classic Generative Adversarial Net and its variants can be roughly categorized into two large families: the unregularized ver- sus regularized GANs. By relaxing the non-parametric assumption on the discriminator in t…
Disentangling Adversarial Robustness and Generalization
Obtaining deep networks that are robust against adversarial examples and generalize well is an open problem. A recent hypothesis even states that both robust and accurate models are impossible, i.e., adversarial robustne…
Adversarial RobustnessDetection of Adversarial Attacks and Characterization of Adversarial Subspace
Adversarial attacks have always been a serious threat for any data-driven model. In this paper, we explore subspaces of adversarial examples in unitary vector domain, and we propose a novel detector for defending our mod…
BenchmarkingEnvironmental Sound ClassificationregressionSound Classification