mlsanityData to 7 Oct 2026

Deep Bayesian Image Set Classification: A Defence Approach against Adversarial Attacks

arXiv 2108.10217 ↗First posted 23 Aug 2021cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Deep learning has become an integral part of various computer vision systems in recent years due to its outstanding achievements for object recognition, facial recognition, and scene understanding. However, deep neural networks (DNNs) are susceptible to be fooled with nearly high confidence by an adversary. In practice, the vulnerability of deep learning systems against carefully perturbed images, known as adversarial examples, poses a dire security threat in the physical world applications. To address this phenomenon, we present, what to our knowledge, is the first ever image set based adversarial defence approach. Image set classification has shown an exceptional performance for object and face recognition, owing to its intrinsic property of handling appearance variability. We propose a robust deep Bayesian image set classification as a defence framework against a broad range of adversarial attacks. We extensively experiment the performance of the proposed technique with several voting strategies. We further analyse the effects of image size, perturbation magnitude, along with the ratio of perturbed images in each image set. We also evaluate our technique with the recent state-of-the-art defence methods, and single-shot recognition task. The empirical results demonstrate superior performance on CIFAR-10, MNIST, ETH-80, and Tiny ImageNet datasets.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 44 of its 72 references that are in the map. First posted on arXiv 23 Aug 2021.

Builds on

44 of 72 references.

References · 44

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  6. 2013Intriguing properties of neural networkscited by 5,114
  7. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  8. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  9. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  10. 2016Adversarial examples in the physical worldcited by 1,762
  11. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  12. 2016Adversarial Machine Learning at Scalecited by 934
32 more
  1. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  2. 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
  3. 2016Universal adversarial perturbationscited by 774
  4. 2020Fast is better than free: Revisiting adversarial trainingcited by 723
  5. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
  6. 2019Adversarial Training for Free!cited by 638
  7. 2017One pixel attack for fooling deep neural networkscited by 579
  8. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 542
  9. 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 530
  10. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 459
  11. 2017Adversarial Examples: Attacks and Defenses for Deep Learningcited by 350
  12. 2014Caffe: Convolutional Architecture for Fast Feature Embeddingcited by 287
  13. 2017MagNet: a Two-Pronged Defense against Adversarial Examplescited by 268
  14. 2017Detecting Adversarial Samples from Artifactscited by 244
  15. 2018Adversarial Logit Pairingcited by 224
  16. 2018Adversarial Robustness Toolbox v1.0.0cited by 214
  17. 2017On the (Statistical) Detection of Adversarial Examplescited by 180
  18. 2018Understanding Measures of Uncertainty for Adversarial Example Detectioncited by 177
  19. 2017The Space of Transferable Adversarial Examplescited by 156
  20. 2016Adversarial Examples Detection in Deep Networks with Convolutional Filter Statisticscited by 77
  21. 2017Fast Feature Fool: A data independent approach to universal adversarial perturbationscited by 65
  22. 2019ME-Net: Towards Effective Adversarial Robustness with Matrix Estimationcited by 65
  23. 2018Adversarial Examples: Opportunities and Challengescited by 62
  24. 2018Adversarial Attacks Against Medical Deep Learning Systemscited by 61
  25. 2017Adversarial Examples, Uncertainty, and Transfer Testing Robustness in Gaussian Process Hybrid Deep Networkscited by 48
  26. 2018Bilateral Adversarial Training: Towards Fast Training of More Robust Models Against Adversarial Attackscited by 48
  27. 2017Robustness to Adversarial Examples through an Ensemble of Specialistscited by 21
  28. 2017Intriguing Properties of Adversarial Examplescited by 20
  29. 2017Blocking Transferability of Adversarial Examples in Black-Box Learning Systemscited by 19
  30. 2017Is Deep Learning Safe for Robot Vision? Adversarial Examples against the iCub Humanoidcited by 19
  31. 2017Efficient Image Set Classification using Linear Regression based Image Reconstructioncited by 2
  32. 2018Real Time Surveillance for Low Resolution and Limited-Data Scenarios: An Image Set Classification Approachcited by 1

Built on by

Not cited yet.