Evaluating Robustness of Deep Image Super-Resolution Against Adversarial Attacks

  title={Evaluating Robustness of Deep Image Super-Resolution Against Adversarial Attacks},
  author={J. Choi and Huan Zhang and J. Kim and Cho-Jui Hsieh and J. Lee},
  journal={2019 IEEE/CVF International Conference on Computer Vision (ICCV)},
  • J. Choi, Huan Zhang, +2 authors J. Lee
  • Published 2019
  • Computer Science
  • 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
  • Single-image super-resolution aims to generate a high-resolution version of a low-resolution image, which serves as an essential component in many image processing applications. This paper investigates the robustness of deep learning-based super-resolution methods against adversarial attacks, which can significantly deteriorate the super-resolved images without noticeable distortion in the attacked low-resolution images. It is demonstrated that state-of-the-art deep super-resolution methods are… CONTINUE READING
    W2S: A Joint Denoising and Super-Resolution Dataset
    • 6
    • Highly Influenced
    Appending Adversarial Frames for Universal Video Attack
    • 2
    • PDF
    Improving Robustness of Deep-Learning-Based Image Reconstruction
    • 1
    • PDF
    Learning to Have an Ear for Face Super-Resolution
    • 1
    • PDF
    Srzoo: An Integrated Repository For Super-Resolution Using Deep Learning
    Microscopy Image Restoration using Deep Learning on W2S
    Learning Loss for Test-Time Augmentation


    Publications referenced by this paper.
    Universal Adversarial Perturbations
    • 911
    • PDF
    ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
    • 487
    • Highly Influential
    • PDF
    Learning a Deep Convolutional Network for Image Super-Resolution
    • 2,157
    • PDF
    Enhanced Deep Residual Networks for Single Image Super-Resolution
    • 1,312
    • Highly Influential
    • PDF
    Image Super-Resolution as a Defense Against Adversarial Attacks
    • 21
    • PDF
    Mitigating adversarial effects through randomization
    • 346
    • PDF
    Explaining and Harnessing Adversarial Examples
    • 5,490
    • PDF
    Adversarial Machine Learning at Scale
    • 1,083
    • Highly Influential
    • PDF
    Delving into Transferable Adversarial Examples and Black-box Attacks
    • 684
    • PDF
    Generative Adversarial Nets
    • 17,848
    • PDF