Online Alternate Generator Against Adversarial Attacks

Li, Haofeng; Zeng, Yirui; Li, Guanbin; Lin, Liang; Yu, Yizhou

doi:10.1109/tip.2020.3025404

Cited by 6 publications

(2 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many defense methods and robust models [11,38,45,68] which have been developed to resist adversarial attacks, attempt to remove, destroy or adapt to adversarial noises. Adversarial training [47,52,67] is a large group of defense methods that trains the target network with adversarial samples and are effective against white-box attacks.…”

Section: Adversarial Attacks and Defensesmentioning

confidence: 99%

Robust Real-World Image Super-Resolution against Adversarial Attacks

Yue

Wei

et al. 2021

Proceedings of the 29th ACM International Conference on Multimedia

Self Cite

View full text Add to dashboard Cite

Recently deep neural networks (DNNs) have achieved significant success in real-world image super-resolution (SR). However, adversarial image samples with quasi-imperceptible noises could threaten deep learning SR models. In this paper, we propose a robust deep learning framework for real-world SR that randomly erases potential adversarial noises in the frequency domain of input images or features. The rationale is that on the SR task clean images or features have a different pattern from the attacked ones in the frequency domain. Observing that existing adversarial attacks usually add high-frequency noises to input images, we introduce a novel random frequency mask module that blocks out high-frequency components possibly containing the harmful perturbations in a stochastic manner. Since the frequency masking may not only destroys the adversarial perturbations but also affects the sharp details in a clean image, we further develop an adversarial sample classifier based on the frequency domain of images to determine if applying the proposed mask module. Based on the above ideas, we devise a novel real-world image SR framework that combines the proposed frequency mask modules and the proposed adversarial classifier with an existing super-resolution backbone network. Experiments show that our proposed method is more insensitive to adversarial attacks and presents more stable SR results than existing models and defenses. CCS CONCEPTS• Computing methodologies → Image processing.

show abstract

Section: Adversarial Attacks and Defensesmentioning

confidence: 99%

Robust Real-World Image Super-Resolution against Adversarial Attacks

Yue

Wei

et al. 2021

Proceedings of the 29th ACM International Conference on Multimedia

Self Cite

View full text Add to dashboard Cite

show abstract

“…There is a work implementing a generator for synthesizing images [37], its authors use incomparable CNN model and datasets; 5.…”

Section: Introductionmentioning

confidence: 99%

Low-Pass Image Filtering to Achieve Adversarial Robustness

Ziyadinov,

Tereshonok

2023

Sensors

View full text Add to dashboard Cite

In this paper, we continue the research cycle on the properties of convolutional neural network-based image recognition systems and ways to improve noise immunity and robustness. Currently, a popular research area related to artificial neural networks is adversarial attacks. The adversarial attacks on the image are not highly perceptible to the human eye, and they also drastically reduce the neural network’s accuracy. Image perception by a machine is highly dependent on the propagation of high frequency distortions throughout the network. At the same time, a human efficiently ignores high-frequency distortions, perceiving the shape of objects as a whole. We propose a technique to reduce the influence of high-frequency noise on the CNNs. We show that low-pass image filtering can improve the image recognition accuracy in the presence of high-frequency distortions in particular, caused by adversarial attacks. This technique is resource efficient and easy to implement. The proposed technique makes it possible to measure up the logic of an artificial neural network to that of a human, for whom high-frequency distortions are not decisive in object recognition.

show abstract

LD-GAN: Learning perturbations for adversarial defense based on GAN structure

Nie

2022

Signal Processing: Image Communication

View full text Add to dashboard Cite

Online Alternate Generator Against Adversarial Attacks

Cited by 6 publications

References 25 publications

Robust Real-World Image Super-Resolution against Adversarial Attacks

Robust Real-World Image Super-Resolution against Adversarial Attacks

Low-Pass Image Filtering to Achieve Adversarial Robustness

LD-GAN: Learning perturbations for adversarial defense based on GAN structure

Contact Info

Product

Resources

About