mlsanityData to 7 Oct 2026

Improving the Transferability of Adversarial Examples with New Iteration Framework and Input Dropout

arXiv 2106.01617 ↗First posted 3 Jun 2021cs.LG cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Deep neural networks(DNNs) is vulnerable to be attacked by adversarial examples. Black-box attack is the most threatening attack. At present, black-box attack methods mainly adopt gradient-based iterative attack methods, which usually limit the relationship between the iteration step size, the number of iterations, and the maximum perturbation. In this paper, we propose a new gradient iteration framework, which redefines the relationship between the above three. Under this framework, we easily improve the attack success rate of DI-TI-MIM. In addition, we propose a gradient iterative attack method based on input dropout, which can be well combined with our framework. We further propose a multi dropout rate version of this method. Experimental results show that our best method can achieve attack success rate of 96.2% for defense model on average, which is higher than the state-of-the-art gradient-based attacks.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 28 of its 36 references that are in the map. First posted on arXiv 3 Jun 2021.

Builds on

28 of 36 references.

References · 28

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  6. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  7. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  8. 2018YOLOv3: An Incremental Improvementcited by 2,652
  9. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
  10. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  11. 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
  12. 2019Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailmentcited by 663
16 more
  1. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 656
  2. 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 591
  3. 2019Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attackscited by 440
  4. 2019Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attackscited by 352
  5. 2018Feature Denoising for Improving Adversarial Robustnesscited by 312
  6. 2018Audio Adversarial Examples: Targeted Attacks on Speech-to-Textcited by 268
  7. 2018Generating Adversarial Examples with Adversarial Networkscited by 256
  8. 2019AdvHat: Real-world adversarial attack on ArcFace Face ID systemcited by 161
  9. 2017Vulnerability of Deep Reinforcement Learning to Policy Induction Attackscited by 91
  10. 2020Patch-wise Attack for Fooling Deep Neural Networkcited by 78
  11. 2018Learning Transferable Adversarial Examples via Ghost Networkscited by 69
  12. 2017Adversarial Transformation Networks: Learning to Generate Adversarial Examplescited by 60
  13. 2018Understanding and Enhancing the Transferability of Adversarial Examplescited by 41
  14. 2020Adversarial Light Projection Attacks on Face Recognition Systems: A Feasibility Studycited by 40
  15. 2018Defensive Dropout for Hardening Deep Neural Networks under Adversarial Attackscited by 13
  16. 2021Staircase Sign Method for Boosting Adversarial Attackscited by 12

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 3; 2025: 1.

5 papers.

  1. 2024Learning to Transform Dynamically for Better Adversarial Transferabilitycited by 23
  2. 2024Bag of Tricks to Boost Adversarial Transferabilitycited by 12
  3. 2025Harnessing the Computation Redundancy in ViTs to Boost Adversarial Transferabilitycited by 4
  4. 2023Building an Invisible Shield for Your Portrait against Deepfakescited by 1
  5. 2024Universal Multi-view Black-box Attack against Object Detectors via Layout Optimizationcited by 0