mlsanityData to 14 Oct 2026

Visualizing Representations of Adversarially Perturbed Inputs

arXiv 2105.14116 ↗First posted 28 May 2021cs.LG cs.HCcited by 0

Not on the map. Why?

Abstract (arXiv)

It has been shown that deep learning models are vulnerable to adversarial attacks. We seek to further understand the consequence of such attacks on the intermediate activations of neural networks. We present an evaluation metric, POP-N, which scores the effectiveness of projecting data to N dimensions under the context of visualizing representations of adversarially perturbed inputs. We conduct experiments on CIFAR-10 to compare the POP-2 score of several dimensionality reduction algorithms across various adversarial attacks. Finally, we utilize the 2D data corresponding to high POP-2 scores to generate example visualizations.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 16 of its 23 references that are in the map. First posted on arXiv 28 May 2021.

Builds on

16 of 23 references.

References · 16

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  5. 2013Intriguing properties of neural networkscited by 5,155
  6. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  7. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,898
  8. 2016Adversarial examples in the physical worldcited by 1,769
  9. 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 536
  10. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 460
  11. 2018Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionalitycited by 282
  12. 2016Technical Report on the CleverHans v2.1.0 Adversarial Examples Librarycited by 124
4 more
  1. 2020Parametric UMAP embeddings for representation and semi-supervised learningcited by 104
  2. 2015Exploring the Space of Adversarial Imagescited by 28
  3. 2019Interpreting Adversarial Examples by Activation Promotion and Suppressioncited by 17
  4. 2017Adversarial-Playground: A Visualization Suite Showing How Adversarial Examples Fool Deep Learningcited by 8

Built on by

Not cited yet.