Retrieval-Augmented Convolutional Neural Networks Against Adversarial Examples

We propose a retrieval-augmented convolutional network (RaCNN) 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 seven readilyavailable adversarial attacks on three datasets–CIFAR-10, SVHN and ImageNet–demonstrate the improved robustness compared to a vanilla convolutional network, and comparable performance with the state-of-the-art reactive defense approaches.

[1]  Richard Shin.  JPEG-resistant Adversarial Images , 2017 .

[2]  Alex Graves,et al.  Conditional Image Generation with PixelCNN Decoders , 2016, NIPS.

[3]  David A. Wagner,et al.  Towards Evaluating the Robustness of Neural Networks , 2016, 2017 IEEE Symposium on Security and Privacy (SP).

[4]  Andrew Y. Ng,et al.  Reading Digits in Natural Images with Unsupervised Feature Learning , 2011 .

[5]  Yoshua Bengio,et al.  Better Mixing via Deep Representations , 2012, ICML.

[6]  Jiajun Zhang,et al.  One Sentence One Model for Neural Machine Translation , 2018, LREC.

[7]  Eduardo Valle,et al.  Exploring the space of adversarial images , 2015, 2016 International Joint Conference on Neural Networks (IJCNN).

[8]  Alexei A. Efros,et al.  Image quilting for texture synthesis and transfer , 2001, SIGGRAPH.

[9]  Razvan Pascanu,et al.  Memory-based Parameter Adaptation , 2018, ICLR.

[10]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[11]  David Wagner,et al.  Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods , 2017, AISec@CCS.

[12]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[13]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[14]  Seyed-Mohsen Moosavi-Dezfooli,et al.  DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[16]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Martin Wattenberg,et al.  Adversarial Spheres , 2018, ICLR.

[18]  Heikki Mannila,et al.  Random projection in dimensionality reduction: applications to image and text data , 2001, KDD '01.

[19]  Jorge Nocedal,et al.  Algorithm 778: L-BFGS-B: Fortran subroutines for large-scale bound-constrained optimization , 1997, TOMS.

[20]  Nicole Immorlica,et al.  Locality-sensitive hashing scheme based on p-stable distributions , 2004, SCG '04.

[21]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[22]  Jonathon Shlens,et al.  Explaining and Harnessing Adversarial Examples , 2014, ICLR.

[23]  Harini Kannan,et al.  Adversarial Logit Pairing , 2018, NIPS 2018.

[24]  Jeff Johnson,et al.  Billion-Scale Similarity Search with GPUs , 2017, IEEE Transactions on Big Data.

[25]  Simon Haykin,et al.  GradientBased Learning Applied to Document Recognition , 2001 .

[26]  L. Rudin,et al.  Nonlinear total variation based noise removal algorithms , 1992 .

[27]  Pascal Vincent,et al.  Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion , 2010, J. Mach. Learn. Res..

[28]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[29]  Alex Krizhevsky,et al.  Learning Multiple Layers of Features from Tiny Images , 2009 .

[30]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[31]  Christopher D. Manning,et al.  Effective Approaches to Attention-based Neural Machine Translation , 2015, EMNLP.

[32]  Joan Bruna,et al.  Intriguing properties of neural networks , 2013, ICLR.

[33]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[34]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[35]  Hongyi Zhang,et al.  mixup: Beyond Empirical Risk Minimization , 2017, ICLR.

[36]  Fei-Fei Li,et al.  ImageNet: A large-scale hierarchical image database , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.