Detect and Defense Against Adversarial Examples in Deep Learning using Natural Scene Statistics and Adaptive Denoising
Not on the map. Why?
Abstract (arXiv)
Despite the enormous performance of deepneural networks (DNNs), recent studies have shown theirvulnerability to adversarial examples (AEs), i.e., care-fully perturbed inputs designed to fool the targetedDNN. Currently, the literature is rich with many ef-fective attacks to craft such AEs. Meanwhile, many de-fenses strategies have been developed to mitigate thisvulnerability. However, these latter showed their effec-tiveness against specific attacks and does not general-ize well to different attacks. In this paper, we proposea framework for defending DNN classifier against ad-versarial samples. The proposed method is based on atwo-stage framework involving a separate detector anda denoising block. The detector aims to detect AEs bycharacterizing them through the use of natural scenestatistic (NSS), where we demonstrate that these statis-tical features are altered by the presence of adversarialperturbations. The denoiser is based on block matching3D (BM3D) filter fed by an optimum threshold valueestimated by a convolutional neural network (CNN) toproject back the samples detected as AEs into theirdata manifold. We conducted a complete evaluation onthree standard datasets namely MNIST, CIFAR-10 andTiny-ImageNet. The experimental results show that theproposed defense method outperforms the state-of-the-art defense techniques by improving the robustnessagainst a set of attacks under black-box, gray-box and white-box settings. The source code is available at: https://github.com/kherchouche-anouar/2DAE
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 46 of its 74 references that are in the map. First posted on arXiv 12 Jul 2021.
Builds on
46 of 74 references.
References · 46
- 2014Microsoft COCO: Common Objects in Contextcited by 17,608
- 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
- 2013Intriguing properties of neural networkscited by 5,155
- 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
- 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
- 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,268
- 2016Adversarial Machine Learning at Scalecited by 936
- 2016Pixel Recurrent Neural Networkscited by 816
- 2020On Adaptive Attacks to Adversarial Example Defensescited by 555
34 more
- 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 546
- 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 468
- 2019On Evaluating Adversarial Robustnesscited by 447
- 2017Mitigating Adversarial Effects Through Randomizationcited by 383
- 2018Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscited by 362
- 2019SelectiveNet: A Deep Neural Network with an Integrated Reject Optioncited by 350
- 2018Adversarially Robust Generalization Requires More Datacited by 318
- 2018Feature Denoising for Improving Adversarial Robustnesscited by 314
- 2018Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionalitycited by 282
- 2017MagNet: a Two-Pronged Defense against Adversarial Examplescited by 269
- 2017Detecting Adversarial Samples from Artifactscited by 245
- 2017PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examplescited by 244
- 2017Benchmarking Denoising Algorithms with Real Photographscited by 209
- 2016A study of the effect of JPG compression on adversarial imagescited by 197
- 2017On the (Statistical) Detection of Adversarial Examplescited by 180
- 2018Certified Adversarial Robustness with Additive Noisecited by 180
- 2018Stochastic Activation Pruning for Robust Adversarial Defensecited by 171
- 2017Towards Robust Neural Networks via Random Self-ensemblecited by 159
- 2014Towards Deep Neural Network Architectures Robust to Adversarial Examplescited by 146
- 2018Benchmarking Neural Network Robustness to Common Corruptions and Surface Variationscited by 99
- 2016Adversarial Examples Detection in Deep Networks with Convolutional Filter Statisticscited by 77
- 2017SafetyNet: Detecting and Rejecting Adversarial Examples Robustlycited by 76
- 2019ME-Net: Towards Effective Adversarial Robustness with Matrix Estimationcited by 65
- 2017Efficient Defenses Against Adversarial Attackscited by 53
- 2017Synthesizing Robust Adversarial Examplescited by 39
- 2016Early Methods for Detecting Adversarial Imagescited by 36
- 2019Adversarial Examples in Modern Machine Learning: A Reviewcited by 36
- 2016Globally Normalized Transition-Based Neural Networkscited by 26
- 2017Generative Adversarial Trainer: Defense to Adversarial Perturbations with GANcited by 20
- 2017Provably Minimally-Distorted Adversarial Examplescited by 12
- 2019Perceptual Evaluation of Adversarial Attacks for CNN-based Image Classificationcited by 12
- 2021Revisiting Model's Uncertainty and Confidences for Adversarial Example Detectioncited by 9
- 2020RAID: Randomized Adversarial-Input Detection for Neural Networkscited by 8
- 2020CNN-Based Real-Time Parameter Tuning for Optimizing Denoising Filter Performancecited by 1
Built on by
Citing papers per year: 2022: 1; 2023: 2.
3 papers.