Evaluating Robustness of Deep Image Super-Resolution Against Adversarial Attacks

Choi, Jun‐Ho; Zhang, Huan; Kim, Junhyuk; Hsieh, Cho‐Jui; Lee, Jong-Seok

doi:10.1109/iccv.2019.00039

Cited by 53 publications

(33 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…clean inputs [20] and have shown to fail to be robust to many adversarial attacks [21], [34]. Instead of attempting to modify inputs, RAILS evolves a statistical population of clones of the input, resulting in enhancing resilience to attacks.…”

Section: A Related Workmentioning

confidence: 99%

RAILS: A Robust Adversarial Immune-Inspired Learning System

et al. 2022

View full text Add to dashboard Cite

Adversarial attacks against deep neural networks (DNNs) are continuously evolving, requiring increasingly powerful defense strategies. We develop a novel adversarial defense framework inspired by the adaptive immune system: the Robust Adversarial Immune-inspired Learning System (RAILS). Initializing a population of exemplars that is balanced across classes, RAILS starts from a uniform label distribution that encourages diversity and uses an evolutionary optimization process to adaptively adjust the predictive label distribution in a manner that emulates the way the natural immune system recognizes novel pathogens. RAILS' evolutionary optimization process explicitly captures the tradeoff between robustness (diversity) and accuracy (specificity) of the network, and represents a new immune-inspired perspective on adversarial learning. The benefits of RAILS are empirically demonstrated under eight types of adversarial attacks on a DNN adversarial image classifier for several benchmark datasets, including: MNIST; SVHN; CIFAR-10; and CIFAR-10. We find that PGD is the most damaging attack strategy and that for this attack RAILS is significantly more robust than other methods, achieving improvements in adversarial robustness by ≥ 5.62%, 12.5%, 10.32%, and 8.39%, on these respective datasets, without appreciable loss of classification accuracy. Codes for the results in this paper are available at https://github.com/wangren09/RAILS.INDEX TERMS Bio-inspired deep learning, adversarial robustness, deep network defense strategies.

show abstract

Section: A Related Workmentioning

confidence: 99%

RAILS: A Robust Adversarial Immune-Inspired Learning System

et al. 2022

View full text Add to dashboard Cite

show abstract

“…3 Proposed Method 3.1 Motivation (Choi et al 2019) showed that SISR networks perform poorly on unseen degradations. In order to train a robust facial SISR network for real-world application, we would therefore need a dataset with paired examples of degraded LR and clean HR images.…”

Section: Adversarial Robustnessmentioning

confidence: 99%

Robust Unpaired Single Image Super-Resolution of Faces

Goswami¹,

A.N²

2022

Preprint

View full text Add to dashboard Cite

We propose an adversarial attack for facial class-specific Single Image Super-Resolution (SISR) methods. Existing attacks, such as the Fast Gradient Sign Method (FGSM) or the Projected Gradient Descent (PGD) method, are either fast but ineffective, or effective but prohibitively slow on these networks. By closely inspecting the surface that the MSE loss, used to train such networks, traces under varying degradations, we were able to identify its parameterizable property. We leverage this property to propose an adverasrial attack that is able to locate the optimum degradation (effective) without needing multiple gradient-ascent steps (fast). Our experiments show that the proposed method is able to achieve a better speed vs effectiveness trade-off than the state-of-theart adversarial attacks, such as FGSM and PGD, for the task of unpaired facial as well as class-specific SISR.

show abstract

“…In addition, when one needs to use the models to build an extension of the super-resolution task, it is necessary to implement it repeatedly for all the frameworks. Examples of the extension include image classification using super-resolved images [12] and robustness analysis of superresolution against adversarial perturbations [13].…”

Section: Models With Different Frameworkmentioning

confidence: 99%

“…In addition, the provided superresolution models can be used to thoroughly analyze their intermediate processes by computing the features and gradients. One example use case is to examine the robustness of the super-resolution models by adding a small perturbation to a given input image, which erroneously deteriorates the super-resolved outputs [13]. Therefore, SRZoo can be employed as a testbed to analyze and refine the state-of-the-art deep learning-based super-resolution methods.…”

Section: Extension To Advanced Topicsmentioning

confidence: 99%

Srzoo: An Integrated Repository For Super-Resolution Using Deep Learning

Choi

Kim

Lee

2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

Deep learning-based image processing algorithms, including image super-resolution methods, have been proposed with significant improvement in performance in recent years. However, their implementations and evaluations are dispersed in terms of various deep learning frameworks and various evaluation criteria. In this paper, we propose an integrated repository for the super-resolution tasks, named SRZoo, to provide state-of-the-art super-resolution models in a single place. Our repository offers not only converted versions of existing pre-trained models, but also documentation and toolkits for converting other models. In addition, SRZoo provides platform-agnostic image reconstruction tools to obtain super-resolved images and evaluate the performance in place. It also brings the opportunity of extension to advanced image-based researches and other image processing models. The software, documentation, and pre-trained models are publicly available on GitHub 1 .

show abstract

Evaluating Robustness of Deep Image Super-Resolution Against Adversarial Attacks

Cited by 53 publications

References 19 publications

RAILS: A Robust Adversarial Immune-Inspired Learning System

RAILS: A Robust Adversarial Immune-Inspired Learning System

Robust Unpaired Single Image Super-Resolution of Faces

Srzoo: An Integrated Repository For Super-Resolution Using Deep Learning

Contact Info

Product

Resources

About