mlsanityData to 7 Oct 2026

On Procedural Adversarial Noise Attack And Defense

arXiv 2108.04409 ↗First posted 10 Aug 2021cs.LG cs.AI cs.CRcited by 0

Not on the map. Why?

Abstract (arXiv)

Deep Neural Networks (DNNs) are vulnerable to adversarial examples which would inveigle neural networks to make prediction errors with small perturbations on the input images. Researchers have been devoted to promoting the research on the universal adversarial perturbations (UAPs) which are gradient-free and have little prior knowledge on data distributions. Procedural adversarial noise attack is a data-free universal perturbation generation method. In this paper, we propose two universal adversarial perturbation (UAP) generation methods based on procedural noise functions: Simplex noise and Worley noise. In our framework, the shading which disturbs visual classification is generated with rendering technology. Without changing the semantic representations, the adversarial examples generated via our methods show superior performance on the attack.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 54 of its 74 references that are in the map. First posted on arXiv 10 Aug 2021.

Builds on

54 of 74 references.

References · 54

  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. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  6. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  7. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  8. 2017Squeeze-and-Excitation Networkscited by 4,763
  9. 2014Going Deeper with Convolutionscited by 4,231
  10. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  11. 2016Adversarial examples in the physical worldcited by 1,762
  12. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
38 more
  1. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
  2. 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
  3. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  4. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  5. 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
  6. 2015The Limitations of Deep Learning in Adversarial Settingscited by 784
  7. 2016Universal adversarial perturbationscited by 774
  8. 2013Network In Networkcited by 600
  9. 2018Black-box Adversarial Attacks with Limited Queries and Informationcited by 499
  10. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 484
  11. 2017Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Modelscited by 459
  12. 2019On Evaluating Adversarial Robustnesscited by 442
  13. 2017Mitigating Adversarial Effects Through Randomizationcited by 382
  14. 2018Feature Denoising for Improving Adversarial Robustnesscited by 312
  15. 2019High Frequency Component Helps Explain the Generalization of Convolutional Neural Networkscited by 310
  16. 2019A Fourier Perspective on Model Robustness in Computer Visioncited by 288
  17. 2019Simple Black-box Adversarial Attackscited by 249
  18. 2017Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradientscited by 236
  19. 2018Adversarial Logit Pairingcited by 224
  20. 2018Adversarial Risk and the Dangers of Evaluating Against Weak Attackscited by 221
  21. 2019Improving Adversarial Robustness via Promoting Ensemble Diversitycited by 213
  22. 2016A study of the effect of JPG compression on adversarial imagescited by 196
  23. 2018Training behavior of deep neural network in frequency domaincited by 174
  24. 2017Towards Robust Neural Networks via Random Self-ensemblecited by 158
  25. 2018Scaling provable adversarial defensescited by 141
  26. 2018Are adversarial examples inevitable?cited by 113
  27. 2019NATTACK: Learning the Distributions of Adversarial Examples for an Improved Black-Box Attack on Deep Neural Networkscited by 94
  28. 2018Generalizable Data-free Objective for Crafting Universal Adversarial Perturbationscited by 88
  29. 2018Adversarial vulnerability for any classifiercited by 78
  30. 2017Fast Feature Fool: A data independent approach to universal adversarial perturbationscited by 65
  31. 2017NAG: Network for Adversary Generationcited by 51
  32. 2019Machine Learning from a Continuous Viewpointcited by 50
  33. 2017Art of singular vectors and universal adversarial perturbationscited by 49
  34. 2019Parsimonious Black-Box Adversarial Attacks via Efficient Combinatorial Optimizationcited by 49
  35. 2018Deep Defense: Training DNNs with Improved Adversarial Robustnesscited by 41
  36. 2019Defending against Whitebox Adversarial Attacks via Randomized Discretizationcited by 29
  37. 2018Procedural Noise Adversarial Examples for Black-Box Attacks on Deep Convolutional Networkscited by 21
  38. 2020Neural Anisotropy Directionscited by 17

50 most cited of 54 All 54 (JSON)

Built on by

Not cited yet.