mlsanityData to 7 Oct 2026

Consistent Semantic Attacks on Optical Flow

arXiv 2111.08485 ↗First posted 16 Nov 2021cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

We present a novel approach for semantically targeted adversarial attacks on Optical Flow. In such attacks the goal is to corrupt the flow predictions of a specific object category or instance. Usually, an attacker seeks to hide the adversarial perturbations in the input. However, a quick scan of the output reveals the attack. In contrast, our method helps to hide the attackers intent in the output as well. We achieve this thanks to a regularization term that encourages off-target consistency. We perform extensive tests on leading optical flow models to demonstrate the benefits of our approach in both white-box and black-box settings. Also, we demonstrate the effectiveness of our attack on subsequent tasks that depend on the optical flow.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 36 of its 54 references that are in the map. First posted on arXiv 16 Nov 2021.

Builds on

36 of 54 references.

References · 36

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  3. 2013Intriguing properties of neural networkscited by 5,114
  4. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  5. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  6. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
  7. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  8. 2016Adversarial examples in the physical worldcited by 1,762
  9. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  10. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,303
  11. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,054
  12. 2017PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volumecited by 966
24 more
  1. 2016Adversarial Machine Learning at Scalecited by 934
  2. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  3. 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
  4. 2016FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networkscited by 780
  5. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  6. 2016Optical Flow Estimation using a Spatial Pyramid Networkcited by 421
  7. 2017On the (Statistical) Detection of Adversarial Examplescited by 180
  8. 2018Disentangling Adversarial Robustness and Generalizationcited by 171
  9. 2019Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimationcited by 131
  10. 2017On the Robustness of Semantic Segmentation Models to Adversarial Attackscited by 126
  11. 2020Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimationcited by 120
  12. 2018Hierarchical Discrete Distribution Decomposition for Match Density Estimationcited by 93
  13. 2019Towards Adversarially Robust Object Detectioncited by 55
  14. 2019Attacking Optical Flowcited by 41
  15. 2020Targeted Adversarial Perturbations for Monocular Depth Predictioncited by 40
  16. 2017Adversarial Examples for Semantic Image Segmentationcited by 33
  17. 2021Binary TTC: A Temporal Geofence for Autonomous Navigationcited by 20
  18. 2021Towards Understanding Adversarial Robustness of Optical Flow Networkscited by 15
  19. 2018Adversarial Attacks for Optical Flow-Based Action Recognition Classifierscited by 14
  20. 2020Probabilistic Pixel-Adaptive Refinement Networkscited by 8
  21. 2020Pick-Object-Attack: Type-Specific Adversarial Attack for Object Detectioncited by 8
  22. 2019Forecasting Time-to-Collision from Monocular Video: Feasibility, Dataset, and Challengescited by 5
  23. 2020Fast Local Attack: Generating Local Adversarial Examples for Object Detectorscited by 3
  24. 2019End to end collision avoidance based on optical flow and neural networkscited by 1

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 1; 2025: 1.

4 papers.

  1. 2023Distracting Downpour: Adversarial Weather Attacks for Motion Estimationcited by 15
  2. 2025RobustSpring: Benchmarking Robustness to Image Corruptions for Optical Flow, Scene Flow and Stereocited by 7
  3. 2023Detection Defenses: An Empty Promise against Adversarial Patch Attacks on Optical Flowcited by 6
  4. 2024Benchmarking the Robustness of Optical Flow Estimation to Corruptionscited by 3