---
_id: '10404'
abstract:
- lang: eng
  text: While convolutional neural networks (CNNs) have found wide adoption as state-of-the-art
    models for image-related tasks, their predictions are often highly sensitive to
    small input perturbations, which the human vision is robust against. This paper
    presents Perturber, a web-based application that allows users to instantaneously
    explore how CNN activations and predictions evolve when a 3D input scene is interactively
    perturbed. Perturber offers a large variety of scene modifications, such as camera
    controls, lighting and shading effects, background modifications, object morphing,
    as well as adversarial attacks, to facilitate the discovery of potential vulnerabilities.
    Fine-tuned model versions can be directly compared for qualitative evaluation
    of their robustness. Case studies with machine learning experts have shown that
    Perturber helps users to quickly generate hypotheses about model vulnerabilities
    and to qualitatively compare model behavior. Using quantitative analyses, we could
    replicate users’ insights with other CNN architectures and input images, yielding
    new insights about the vulnerability of adversarially trained models.
acknowledgement: "We thank Robert Geirhos and Roland Zimmermann for their participation
  in the case study and valuable feedback, Chris Olah and Nick Cammarata for valuable
  discussions in the early phase of the project, as well as the Distill Slack workspace
  as a platform for discussions. M.L. is supported in part by the Austrian Science
  Fund (FWF) under grant Z211-N23 (Wittgenstein Award). J.B. is supported by the German
  Federal Ministry of Education and Research\r\n(BMBF) through the Competence Center
  for Machine Learning (TUE.AI, FKZ 01IS18039A) and the International Max Planck Research
  School for Intelligent Systems (IMPRS-IS). R.H. is partially supported by Boeing
  and Horizon-2020 ECSEL (grant 783163, iDev40).\r\n"
article_processing_charge: No
article_type: original
arxiv: 1
author:
- first_name: Stefan
  full_name: Sietzen, Stefan
  last_name: Sietzen
- first_name: Mathias
  full_name: Lechner, Mathias
  id: 3DC22916-F248-11E8-B48F-1D18A9856A87
  last_name: Lechner
- first_name: Judy
  full_name: Borowski, Judy
  last_name: Borowski
- first_name: Ramin
  full_name: Hasani, Ramin
  last_name: Hasani
- first_name: Manuela
  full_name: Waldner, Manuela
  last_name: Waldner
citation:
  ama: Sietzen S, Lechner M, Borowski J, Hasani R, Waldner M. Interactive analysis
    of CNN robustness. <i>Computer Graphics Forum</i>. 2021;40(7):253-264. doi:<a
    href="https://doi.org/10.1111/cgf.14418">10.1111/cgf.14418</a>
  apa: Sietzen, S., Lechner, M., Borowski, J., Hasani, R., &#38; Waldner, M. (2021).
    Interactive analysis of CNN robustness. <i>Computer Graphics Forum</i>. Wiley.
    <a href="https://doi.org/10.1111/cgf.14418">https://doi.org/10.1111/cgf.14418</a>
  chicago: Sietzen, Stefan, Mathias Lechner, Judy Borowski, Ramin Hasani, and Manuela
    Waldner. “Interactive Analysis of CNN Robustness.” <i>Computer Graphics Forum</i>.
    Wiley, 2021. <a href="https://doi.org/10.1111/cgf.14418">https://doi.org/10.1111/cgf.14418</a>.
  ieee: S. Sietzen, M. Lechner, J. Borowski, R. Hasani, and M. Waldner, “Interactive
    analysis of CNN robustness,” <i>Computer Graphics Forum</i>, vol. 40, no. 7. Wiley,
    pp. 253–264, 2021.
  ista: Sietzen S, Lechner M, Borowski J, Hasani R, Waldner M. 2021. Interactive analysis
    of CNN robustness. Computer Graphics Forum. 40(7), 253–264.
  mla: Sietzen, Stefan, et al. “Interactive Analysis of CNN Robustness.” <i>Computer
    Graphics Forum</i>, vol. 40, no. 7, Wiley, 2021, pp. 253–64, doi:<a href="https://doi.org/10.1111/cgf.14418">10.1111/cgf.14418</a>.
  short: S. Sietzen, M. Lechner, J. Borowski, R. Hasani, M. Waldner, Computer Graphics
    Forum 40 (2021) 253–264.
date_created: 2021-12-05T23:01:40Z
date_published: 2021-11-27T00:00:00Z
date_updated: 2025-04-15T06:25:55Z
day: '27'
department:
- _id: ToHe
doi: 10.1111/cgf.14418
external_id:
  arxiv:
  - '2110.07667'
  isi:
  - '000722952000024'
intvolume: '        40'
isi: 1
issue: '7'
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://arxiv.org/abs/2110.07667
month: '11'
oa: 1
oa_version: Preprint
page: 253-264
project:
- _id: 25F42A32-B435-11E9-9278-68D0E5697425
  call_identifier: FWF
  grant_number: Z211
  name: Formal methods for the design and analysis of complex systems
publication: Computer Graphics Forum
publication_identifier:
  eissn:
  - 1467-8659
  issn:
  - 0167-7055
publication_status: published
publisher: Wiley
quality_controlled: '1'
scopus_import: '1'
status: public
title: Interactive analysis of CNN robustness
type: journal_article
user_id: 4359f0d1-fa6c-11eb-b949-802e58b17ae8
volume: 40
year: '2021'
...