Corpus ID: 208291197

Using Depth for Pixel-Wise Detection of Adversarial Attacks in Crowd Counting

@article{Liu2019UsingDF,
  title={Using Depth for Pixel-Wise Detection of Adversarial Attacks in Crowd Counting},
  author={W. Liu and M. Salzmann and P. Fua},
  journal={ArXiv},
  year={2019},
  volume={abs/1911.11484}
}
  • W. Liu, M. Salzmann, P. Fua
  • Published 2019
  • Computer Science
  • ArXiv
  • State-of-the-art methods for counting people in crowded scenes rely on deep networks to estimate crowd density. While effective, deep learning approaches are vulnerable to adversarial attacks, which, in a crowd-counting context, can lead to serious security issues. However, attack and defense mechanisms have been virtually unexplored in regression tasks, let alone for crowd density estimation. In this paper, we investigate the effectiveness of existing attack strategies on crowd-counting… CONTINUE READING
    2 Citations

    Figures, Tables, and Topics from this paper.

    References

    SHOWING 1-10 OF 74 REFERENCES
    Residual Regression With Semantic Prior for Crowd Counting
    • 46
    • PDF
    Point in, Box Out: Beyond Counting Persons in Crowds
    • 45
    • PDF
    Crowd Counting via Adversarial Cross-Scale Consistency Pursuit
    • 151
    • PDF
    Context-Aware Crowd Counting
    • W. Liu, M. Salzmann, P. Fua
    • Computer Science
    • 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
    • 2019
    • 94
    • PDF
    Cross-scene crowd counting via deep convolutional neural networks
    • 620
    • PDF
    Revisiting Perspective Information for Efficient Crowd Counting
    • 69
    • PDF
    Crowd Counting using Deep Recurrent Spatial-Aware Network
    • 82
    • PDF
    Towards Perspective-Free Object Counting with Deep Learning
    • 331
    • PDF
    Attacking Optical Flow
    • 20
    • PDF