mlsanityData to 7 Oct 2026

Defensive Tensorization

arXiv 2110.13859 ↗First posted 26 Oct 2021cs.LG cs.AI cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

We propose defensive tensorization, an adversarial defence technique that leverages a latent high-order factorization of the network. The layers of a network are first expressed as factorized tensor layers. Tensor dropout is then applied in the latent subspace, therefore resulting in dense reconstructed weights, without the sparsity or perturbations typically induced by the randomization.Our approach can be readily integrated with any arbitrary neural architecture and combined with techniques like adversarial training. We empirically demonstrate the effectiveness of our approach on standard image classification benchmarks. We validate the versatility of our approach across domains and low-precision architectures by considering an audio classification task and binary networks. In all cases, we demonstrate improved performance compared to prior works.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 45 of its 58 references that are in the map. First posted on arXiv 26 Oct 2021.

Builds on

45 of 58 references.

References · 45

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  5. 2016Adversarial examples in the physical worldcited by 1,762
  6. 2016Concrete Problems in AI Safetycited by 1,582
  7. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  8. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  9. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  10. 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 829
  11. 2018Speech Commands: A Dataset for Limited-Vocabulary Speech Recognitioncited by 741
  12. 2015BinaryConnect: Training Deep Neural Networks with binary weights during propagationscited by 571
33 more
  1. 2017Countering Adversarial Images using Input Transformationscited by 517
  2. 2020Overfitting in adversarially robust deep learningcited by 504
  3. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 484
  4. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 459
  5. 2017Mitigating Adversarial Effects Through Randomizationcited by 382
  6. 2018Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscited by 362
  7. 2017Adversarial Attacks on Neural Network Policiescited by 314
  8. 2018Feature Denoising for Improving Adversarial Robustnesscited by 312
  9. 2020Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examplescited by 275
  10. 2015Tensorizing Neural Networkscited by 246
  11. 2017PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examplescited by 243
  12. 2019Towards Stable and Efficient Training of Verifiably Robust Neural Networkscited by 204
  13. 2014Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decompositioncited by 199
  14. 2018Stochastic Activation Pruning for Robust Adversarial Defensecited by 171
  15. 2015Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applicationscited by 161
  16. 2017Theoretical insights into the optimization landscape of over-parameterized shallow neural networkscited by 128
  17. 2016TensorLy: Tensor Learning in Pythoncited by 104
  18. 2016Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1cited by 102
  19. 2018On the Power of Over-parametrization in Neural Networks with Quadratic Activationcited by 102
  20. 2019Defensive Quantization: When Efficiency Meets Robustnesscited by 95
  21. 2018Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Networkcited by 68
  22. 2019ME-Net: Towards Effective Adversarial Robustness with Matrix Estimationcited by 65
  23. 2019Adversarial Defense by Restricting the Hidden Space of Deep Neural Networkscited by 56
  24. 2017CP-decomposition with Tensor Power Method for Convolutional Neural Networks Compressioncited by 30
  25. 2017Attacking Binarized Neural Networkscited by 28
  26. 2017Binarized Convolutional Landmark Localizers for Human Pose Estimation and Face Alignment with Limited Resourcescited by 23
  27. 2019T-Net: Parametrizing Fully Convolutional Nets with a Single High-Order Tensorcited by 22
  28. 2015Fast and Guaranteed Tensor Decomposition via Sketchingcited by 19
  29. 2017Foolbox: A Python toolbox to benchmark the robustness of machine learning modelscited by 19
  30. 2018Defensive Dropout for Hardening Deep Neural Networks under Adversarial Attackscited by 13
  31. 2018Combinatorial Attacks on Binarized Neural Networkscited by 11
  32. 2019Randomized Tensor Ring Decomposition and Its Application to Large-scale Data Reconstructioncited by 11
  33. 2014Decomposition of Big Tensors With Low Multilinear Rankcited by 7

Built on by

Cited by year

Citing papers per year: 2023: 1.

1 paper.

  1. 2023Robust Adversarial Defense by Tensor Factorizationcited by 2