A Kernelized Manifold Mapping to Diminish the Effect of Adversarial Perturbations
The linear and non-flexible nature of deep convolutional models makes them vulnerable to carefully crafted adversarial perturbations. To tackle this problem, we propose a non-linear radial basis convolutional feature mapping by learning a Mahalanobis-like distance function. Our method then maps the convolutional features onto a linearly well-separated manifold, which prevents small adversarial perturbations from forcing a sample to cross the decision boundary. We test the proposed method on three publicly available image classification and segmentation datasets namely, MNIST, ISBI ISIC 2017 skin lesion segmentation, and NIH Chest X-Ray-14. We evaluate the robustness of our method to different gradient (targeted and untargeted) and non-gradient based attacks and compare it to several non-gradient masking defense strategies. Our results demonstrate that the proposed method can increase the resilience of deep convolutional neural networks to adversarial perturbations without accuracy drop on clean data.
Code (1)
Tasks
image-classificationImage ClassificationLesion SegmentationSegmentationSkin Lesion SegmentationSimilar Papers 제목 키워드 기반
Action Anticipation with RBF Kernelized Feature Mapping RNN
We introduce a novel Recurrent Neural Network-based algorithm for future video feature generation and action anticipation called feature mapping RNN. Our novel RNN architecture builds upon three effective principles of m…
Action AnticipationExtrinsic Methods for Coding and Dictionary Learning on Grassmann Manifolds
Sparsity-based representations have recently led to notable results in various visual recognition tasks. In a separate line of research, Riemannian manifolds have been shown useful for dealing with features and models th…
Action RecognitionClassificationDictionary LearningFace Recognition+4Kernelized LRR on Grassmann Manifolds for Subspace Clustering
Low rank representation (LRR) has recently attracted great interest due to its pleasing efficacy in exploring low-dimensional sub- space structures embedded in data. One of its successful applications is subspace cluster…
ClusteringKernelized Low Rank Representation on Grassmann Manifolds
Low rank representation (LRR) has recently attracted great interest due to its pleasing efficacy in exploring low-dimensional subspace structures embedded in data. One of its successful applications is subspace clusterin…
ClusteringManifold Regularization for Kernelized LSTD
Policy evaluation or value function or Q-function approximation is a key procedure in reinforcement learning (RL). It is a necessary component of policy iteration and can be used for variance reduction in policy gradient…
Policy Gradient MethodsReinforcement LearningReinforcement Learning (RL)