Retrieval-Augmented Convolutional Neural Networks for Improved Robustness against Adversarial Examples

Abstract

We propose a retrieval-augmented convolutional network and propose to train it with local mixup, a novel variant of the recently proposed mixup algorithm. The proposed hybrid architecture combining a convolutional network and an off-the-shelf retrieval engine was designed to mitigate the adverse effect of off-manifold adversarial examples, while the proposed local mixup addresses on-manifold ones by explicitly encouraging the classifier to locally behave linearly on the data manifold. Our evaluation of the proposed approach against five readily-available adversarial attacks on three datasets--CIFAR-10, SVHN and ImageNet--demonstrate the improved robustness compared to the vanilla convolutional network.

References in corpus (15)

• Adam: A Method for Stochastic Optimization
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• mixup: Beyond Empirical Risk Minimization
• Conditional Image Generation with PixelCNN Decoders
• Towards Deep Neural Network Architectures Robust to Adversarial Examples
• Countering Adversarial Images using Input Transformations
• PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examples
• A study of the effect of JPG compression on adversarial images
• NO Need to Worry about Adversarial Examples in Object Detection in Autonomous Vehicles
• Parseval Networks: Improving Robustness to Adversarial Examples
• Generative Adversarial Trainer: Defense to Adversarial Perturbations with GAN
• Search Engine Guided Non-Parametric Neural Machine Translation
• Generating Sentences by Editing Prototypes
• One Sentence One Model for Neural Machine Translation
• $k$-Nearest Neighbor Augmented Neural Networks for Text Classification

Cited by in corpus (6)

• Generalization through Memorization: Nearest Neighbor Language Models
• Adversarial Examples in Deep Learning: Characterization and Divergence
• A Simple Cache Model for Image Recognition
• Train and You'll Miss It: Interactive Model Iteration with Weak Supervision and Pre-Trained Embeddings
• Improving the robustness of ImageNet classifiers using elements of human visual cognition
• Retrieval & Interaction Machine for Tabular Data Prediction