Intelligent Systems
Note: This research group has relocated. Discover the updated page here

Attacking Optical Flow

2019

Conference Paper

avg

ps


Deep neural nets achieve state-of-the-art performance on the problem of optical flow estimation. Since optical flow is used in several safety-critical applications like self-driving cars, it is important to gain insights into the robustness of those techniques. Recently, it has been shown that adversarial attacks easily fool deep neural networks to misclassify objects. The robustness of optical flow networks to adversarial attacks, however, has not been studied so far. In this paper, we extend adversarial patch attacks to optical flow networks and show that such attacks can compromise their performance. We show that corrupting a small patch of less than 1% of the image size can significantly affect optical flow estimates. Our attacks lead to noisy flow estimates that extend significantly beyond the region of the attack, in many cases even completely erasing the motion of objects in the scene. While networks using an encoder-decoder architecture are very sensitive to these attacks, we found that networks using a spatial pyramid architecture are less affected. We analyse the success and failure of attacking both architectures by visualizing their feature maps and comparing them to classical optical flow techniques which are robust to these attacks. We also demonstrate that such attacks are practical by placing a printed pattern into real scenes.

Author(s): Anurag Ranjan and Joel Janai and Andreas Geiger and Michael J. Black
Book Title: Proceedings International Conference on Computer Vision (ICCV)
Pages: 2404--2413
Year: 2019
Month: November
Day: 2
Publisher: IEEE

Department(s): Autonomous Vision, Perceiving Systems
Research Project(s): Learning Optical Flow
Bibtex Type: Conference Paper (inproceedings)
Paper Type: Conference

DOI: 10.1109/ICCV.2019.00249
Event Name: 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
Event Place: Seoul, South Korea

ISBN: 978-1-7281-4803-8
Note: ISSN: 2380-7504
State: Published
URL: https://flowattack.is.tue.mpg.de/

Links: Video
Project Page
Video:
Attachments: Paper
Supplementary Material

BibTex

@inproceedings{flowattack,
  title = {Attacking Optical Flow},
  author = {Ranjan, Anurag and Janai, Joel and Geiger, Andreas and Black, Michael J.},
  booktitle = {Proceedings International Conference on Computer Vision (ICCV)},
  pages = {2404--2413},
  publisher = {IEEE},
  month = nov,
  year = {2019},
  note = {ISSN: 2380-7504},
  doi = {10.1109/ICCV.2019.00249},
  url = {https://flowattack.is.tue.mpg.de/},
  month_numeric = {11}
}