mlsanityData to 7 Oct 2026

Enhancing Output Diversity Improves Conjugate Gradient-based Adversarial Attacks

arXiv 2408.03972 ↗First posted 7 Aug 2024cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Deep neural networks are vulnerable to adversarial examples, and adversarial attacks that generate adversarial examples have been studied in this context. Existing studies imply that increasing the diversity of model outputs contributes to improving the attack performance. This study focuses on the Auto Conjugate Gradient (ACG) attack, which is inspired by the conjugate gradient method and has a high diversification performance. We hypothesized that increasing the distance between two consecutive search points would enhance the output diversity. To test our hypothesis, we propose Rescaling-ACG (ReACG), which automatically modifies the two components that significantly affect the distance between two consecutive search points, including the search direction and step size. ReACG showed higher attack performance than that of ACG, and is particularly effective for ImageNet models with several classification classes. Experimental results show that the distance between two consecutive search points enhances the output diversity and may help develop new potent attacks. The code is available at urlhttps://github.com/yamamura-k/ReACG

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 32 of its 39 references that are in the map. First posted on arXiv 7 Aug 2024.

Builds on

32 of 39 references.

References · 32

  1. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  6. 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,455
  7. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  8. 2020Fast is better than free: Revisiting adversarial trainingcited by 723
  9. 2020RobustBench: a standardized adversarial robustness benchmarkcited by 659
  10. 2020Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examplescited by 275
  11. 2018Audio Adversarial Examples: Targeted Attacks on Speech-to-Textcited by 268
  12. 2021Improving Robustness using Generated Datacited by 233
20 more
  1. 2020Understanding and Improving Fast Adversarial Trainingcited by 213
  2. 2023Better Diffusion Models Further Improve Adversarial Trainingcited by 207
  3. 2021Data Augmentation Can Improve Robustnesscited by 193
  4. 2021Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?cited by 113
  5. 2022Robustness and Accuracy Could Be Reconcilable by (Proper) Definitioncited by 109
  6. 2023A Comprehensive Study on Robustness of Image Classification Models: Benchmarking and Rethinkingcited by 85
  7. 2023Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threat Modelscited by 79
  8. 2022A Light Recipe to Train Robust Vision Transformerscited by 64
  9. 2023Decoupled Kullback-Leibler Divergence Losscited by 58
  10. 2023Robust Principles: Architectural Design Principles for Adversarially Robust CNNscited by 46
  11. 2019An Alternative Surrogate Loss for PGD-based Adversarial Testingcited by 45
  12. 2022Practical Evaluation of Adversarial Robustness via Adaptive Auto Attackcited by 44
  13. 2022Efficient and Effective Augmentation Strategy for Adversarial Trainingcited by 43
  14. 2020Composite Adversarial Attackscited by 29
  15. 2022Revisiting Residual Networks for Adversarial Robustness: An Architectural Perspectivecited by 28
  16. 2020Miss the Point: Targeted Adversarial Attack on Multiple Landmark Detectioncited by 21
  17. 2023Improving the Accuracy-Robustness Trade-Off of Classifiers via Adaptive Smoothingcited by 18
  18. 2022Diversified Adversarial Attacks based on Conjugate Gradient Methodcited by 11
  19. 2022Reliable Robustness Evaluation via Automatically Constructed Attack Ensemblescited by 6
  20. 2021Constrained Gradient Descent: A Powerful and Principled Evasion Attack Against Neural Networkscited by 4

Built on by

Not cited yet.