Image Super-Resolution as a Defense Against Adversarial Attacks

@article{Mustafa2020ImageSA,
  title={Image Super-Resolution as a Defense Against Adversarial Attacks},
  author={Aamir Mustafa and S. Khan and Munawar Hayat and J. Shen and L. Shao},
  journal={IEEE Transactions on Image Processing},
  year={2020},
  volume={29},
  pages={1711-1724}
}
Convolutional Neural Networks have achieved significant success across multiple computer vision tasks. However, they are vulnerable to carefully crafted, human-imperceptible adversarial noise patterns which constrain their deployment in critical security-sensitive systems. This paper proposes a computationally efficient image enhancement approach that provides a strong defense mechanism to effectively mitigate the effect of such adversarial perturbations. We show that deep image restoration… Expand
Super-Resolution Coding Defense Against Adversarial Examples
A Self-supervised Approach for Adversarial Robustness
Evaluating Robustness of Deep Image Super-Resolution Against Adversarial Attacks
DVAE-SR: denoiser variational auto-encoder and super-resolution to counter adversarial attacks
Review on Image Processing Based Adversarial Example Defenses in Computer Vision
  • Meikang Qiu, Han Qiu
  • Computer Science
  • 2020 IEEE 6th Intl Conference on Big Data Security on Cloud (BigDataSecurity), IEEE Intl Conference on High Performance and Smart Computing, (HPSC) and IEEE Intl Conference on Intelligent Data and Security (IDS)
  • 2020
Adversarial Dual Network Learning With Randomized Image Transform for Restoring Attacked Images
Deeply Supervised Discriminative Learning for Adversarial Defense.
...
1
2
3
4
...

References

SHOWING 1-10 OF 68 REFERENCES
Feature Denoising for Improving Adversarial Robustness
Deflecting Adversarial Attacks with Pixel Deflection
Defense Against Adversarial Attacks Using High-Level Representation Guided Denoiser
Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models
Mitigating adversarial effects through randomization
Improving Transferability of Adversarial Examples With Input Diversity
Keeping the Bad Guys Out: Protecting and Vaccinating Deep Learning with JPEG Compression
Countering Adversarial Images using Input Transformations
A study of the effect of JPG compression on adversarial images
On Detecting Adversarial Perturbations
...
1
2
3
4
5
...