mlsanityData to 7 Oct 2026

Attention-Guided Black-box Adversarial Attacks with Large-Scale Multiobjective Evolutionary Optimization

arXiv 2101.07512 ↗First posted 19 Jan 2021cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Fooling deep neural networks (DNNs) with the black-box optimization has become a popular adversarial attack fashion, as the structural prior knowledge of DNNs is always unknown. Nevertheless, recent black-box adversarial attacks may struggle to balance their attack ability and visual quality of the generated adversarial examples (AEs) in tackling high-resolution images. In this paper, we propose an attention-guided black-box adversarial attack based on the large-scale multiobjective evolutionary optimization, termed as LMOA. By considering the spatial semantic information of images, we firstly take advantage of the attention map to determine the perturbed pixels. Instead of attacking the entire image, reducing the perturbed pixels with the attention mechanism can help to avoid the notorious curse of dimensionality and thereby improves the performance of attacking. Secondly, a large-scale multiobjective evolutionary algorithm is employed to traverse the reduced pixels in the salient region. Benefiting from its characteristics, the generated AEs have the potential to fool target DNNs while being imperceptible by the human vision. Extensive experimental results have verified the effectiveness of the proposed LMOA on the ImageNet dataset. More importantly, it is more competitive to generate high-resolution AEs with better visual quality compared with the existing black-box adversarial attacks.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 37 of its 85 references that are in the map. First posted on arXiv 19 Jan 2021.

Builds on

37 of 85 references.

References · 37

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  5. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  6. 2013Intriguing properties of neural networkscited by 5,114
  7. 2017Squeeze-and-Excitation Networkscited by 4,763
  8. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  9. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  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. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,054
25 more
  1. 2016Adversarial Machine Learning at Scalecited by 934
  2. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  3. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 656
  4. 2017One pixel attack for fooling deep neural networkscited by 579
  5. 2017Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Modelscited by 459
  6. 2019Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attackscited by 440
  7. 2019Simple Black-box Adversarial Attackscited by 249
  8. 2018AutoZOOM: Autoencoder-based Zeroth Order Optimization Method for Attacking Black-box Neural Networkscited by 137
  9. 2019Exploring Randomly Wired Neural Networks for Image Recognitioncited by 103
  10. 2020QEBA: Query-Efficient Boundary-Based Blackbox Attackcited by 103
  11. 2018GenAttack: Practical Black-box Attacks with Gradient-Free Optimizationcited by 82
  12. 2020GeoDA: a geometric framework for black-box adversarial attackscited by 66
  13. 2018Adversarial Examples: Opportunities and Challengescited by 62
  14. 2017Evolving Deep Convolutional Neural Networks for Image Classificationcited by 54
  15. 2017PlatEMO: A MATLAB Platform for Evolutionary Multi-Objective Optimizationcited by 40
  16. 2019Curls & Whey: Boosting Black-Box Adversarial Attackscited by 37
  17. 2019A Survey of Black-Box Adversarial Attacks on Computer Vision Modelscited by 36
  18. 2016Adversarial Diversity and Hard Positive Generationcited by 35
  19. 2019POBA-GA: Perturbation Optimized Black-Box Adversarial Attacks via Genetic Algorithmcited by 14
  20. 2020Detection Defense Against Adversarial Attacks with Saliency Mapcited by 10
  21. 2019Adversarial Example Generation using Evolutionary Multi-objective Optimizationcited by 9
  22. 2019Inspecting adversarial examples using the Fisher informationcited by 7
  23. 2018Towards Query Efficient Black-box Attacks: An Input-free Perspectivecited by 5
  24. 2019A Black-box Attack on Neural Networks Based on Swarm Evolutionary Algorithmcited by 3
  25. 2018A Data-driven Adversarial Examples Recognition Framework via Adversarial Feature Genomecited by 1

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2.

3 papers.

  1. 2023SUNY: A Visual Interpretation Framework for Convolutional Neural Networks from a Necessary and Sufficient Perspectivecited by 5
  2. 2023Adversarial Examples Detection with Enhanced Image Difference Features based on Local Histogram Equalizationcited by 1
  3. 2022Adversarial Example Defense via Perturbation Grading Strategycited by 0