mlsanityData to 14 Oct 2026

DANAA: Towards transferable attacks with double adversarial neuron attribution

arXiv 2310.10427 ↗First posted 16 Oct 2023cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

While deep neural networks have excellent results in many fields, they are susceptible to interference from attacking samples resulting in erroneous judgments. Feature-level attacks are one of the effective attack types, which targets the learnt features in the hidden layers to improve its transferability across different models. Yet it is observed that the transferability has been largely impacted by the neuron importance estimation results. In this paper, a double adversarial neuron attribution attack method, termed `DANAA', is proposed to obtain more accurate feature importance estimation. In our method, the model outputs are attributed to the middle layer based on an adversarial non-linear path. The goal is to measure the weight of individual neurons and retain the features that are more important towards transferability. We have conducted extensive experiments on the benchmark datasets to demonstrate the state-of-the-art performance of our method. Our code is available at: https://github.com/Davidjinzb/DANAA

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 32 of its 38 references that are in the map. First posted on arXiv 16 Oct 2023.

Builds on

32 of 38 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  5. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  6. 2013Intriguing properties of neural networkscited by 5,155
  7. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  8. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  9. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,512
  10. 2016Adversarial Machine Learning at Scalecited by 936
  11. 2016Practical Black-Box Attacks against Machine Learningcited by 903
  12. 2017Ensemble Adversarial Training: Attacks and Defensescited by 840
20 more
  1. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 685
  2. 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 599
  3. 2018Black-box Adversarial Attacks with Limited Queries and Informationcited by 501
  4. 2019Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attackscited by 442
  5. 2018Generating Adversarial Examples with Adversarial Networkscited by 258
  6. 2019The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networkscited by 246
  7. 2021Enhancing the Transferability of Adversarial Attacks through Variance Tuningcited by 244
  8. 2018Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priorscited by 146
  9. 2022Frequency Domain Model Augmentation for Adversarial Attackcited by 130
  10. 2021Feature Importance-aware Transferable Adversarial Attackscited by 127
  11. 2019Improving Black-box Adversarial Attacks with a Transfer-based Priorcited by 121
  12. 2020QEBA: Query-Efficient Boundary-Based Blackbox Attackcited by 104
  13. 2022Improving Adversarial Transferability via Neuron Attribution-Based Attackscited by 93
  14. 2021Stochastic Variance Reduced Ensemble Adversarial Attack for Boosting the Adversarial Transferabilitycited by 84
  15. 2020Patch-wise Attack for Fooling Deep Neural Networkcited by 78
  16. 2020Knowledge-Enriched Distributional Model Inversion Attackscited by 67
  17. 2022Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attackscited by 60
  18. 2019FDA: Feature Disruptive Attackcited by 56
  19. 2018Task-generalizable Adversarial Attack based on Perceptual Metriccited by 18
  20. 2022Boosting Black-Box Adversarial Attacks with Meta Learningcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 5; 2025: 0; 2026: 1.

7 papers.

  1. 2023MFABA: A More Faithful and Accelerated Boundary-based Attribution Method for Deep Neural Networkscited by 7
  2. 2024GE-AdvGAN: Improving the transferability of adversarial samples by gradient editing-based adversarial generative modelcited by 7
  3. 2024Benchmarking Transferable Adversarial Attackscited by 5
  4. 2024DMS: Addressing Information Loss with More Steps for Pragmatic Adversarial Attackscited by 1
  5. 2024Leveraging Information Consistency in Frequency and Spatial Domain for Adversarial Attackscited by 0
  6. 2024Enhancing Transferability of Adversarial Attacks with GE-AdvGAN+: A Comprehensive Framework for Gradient Editingcited by 0
  7. 2026Devling into Adversarial Transferability on Image Classification: Review, Benchmark, and Evaluationcited by 0