mlsanityData to 7 Oct 2026

Multi-step domain adaptation by adversarial attack to H Delta H-divergence

arXiv 2207.08948 ↗First posted 18 Jul 2022cs.LG cs.CR cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Adversarial examples are transferable between different models. In our paper, we propose to use this property for multi-step domain adaptation. In unsupervised domain adaptation settings, we demonstrate that replacing the source domain with adversarial examples to H Delta H-divergence can improve source classifier accuracy on the target domain. Our method can be connected to most domain adaptation techniques. We conducted a range of experiments and achieved improvement in accuracy on Digits and Office-Home datasets.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 15 of its 22 references that are in the map. First posted on arXiv 18 Jul 2022.

Builds on

15 of 22 references.

References · 15

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  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. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  6. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,323
  7. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  8. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,181
  9. 2020Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptationcited by 844
  10. 2018Deep Visual Domain Adaptation: A Surveycited by 634
  11. 2016Deep Transfer Learning with Joint Adaptation Networkscited by 609
  12. 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 439
3 more
  1. 2020Backpropagating Linearly Improves Transferability of Adversarial Examplescited by 79
  2. 2018Towards Imperceptible and Robust Adversarial Example Attacks against Neural Networkscited by 38
  3. 2019Measuring the Transferability of Adversarial Examplescited by 6

Built on by

Not cited yet.