Corpus ID: 208175576

Adversarial Robustness of Flow-Based Generative Models

  title={Adversarial Robustness of Flow-Based Generative Models},
  author={P. Pope and Y. Balaji and S. Feizi},
  • P. Pope, Y. Balaji, S. Feizi
  • Published 2020
  • Computer Science, Mathematics
  • ArXiv
  • Flow-based generative models leverage invertible generator functions to fit a distribution to the training data using maximum likelihood. Despite their use in several application domains, robustness of these models to adversarial attacks has hardly been explored. In this paper, we study adversarial robustness of flow-based generative models both theoretically (for some simple models) and empirically (for more complex ones). First, we consider a linear flow-based generative model and compute… CONTINUE READING
    5 Citations

    Figures, Tables, and Topics from this paper


    Adversarial Examples for Generative Models
    • 159
    • PDF
    Towards Deep Learning Models Resistant to Adversarial Attacks
    • 2,931
    • Highly Influential
    • PDF
    Adversarial Machine Learning at Scale
    • 1,272
    • Highly Influential
    • PDF
    Feature Denoising for Improving Adversarial Robustness
    • 305
    • PDF
    Generative Adversarial Nets
    • 20,850
    • PDF
    Explaining and Harnessing Adversarial Examples
    • 6,521
    • PDF
    Towards Evaluating the Robustness of Neural Networks
    • 3,060
    • PDF
    Glow: Generative Flow with Invertible 1x1 Convolutions
    • 866
    • PDF
    Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
    • C. Ledig, L. Theis, +6 authors W. Shi
    • Computer Science, Mathematics
    • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
    • 2017
    • 4,368
    • PDF