Defense against adversarial attacks using DRAGAN

ArjomandBigdeli, Ali; Amirmazlaghani, Maryam; Khalooei, Mohammad

doi:10.1109/icspis51611.2020.9349536

Cited by 4 publications

(3 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DRAGAN-Defense (Deep Regret Analytic Generative Adversarial Network) [35] is inspired by Defense-GAN [32] and claims to improve its results. DRAGAN is an updated version of GAN that offers fast and stable training and the chance to overcome mode collapse.…”

Section: Defense Methods Against Adversarial Attacksmentioning

confidence: 99%

See 1 more Smart Citation

Defending Adversarial Examples by a Clipped Residual U-Net Model

Ali¹,

Qureshi²,

Bhatti³

et al. 2023

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

Deep learning-based systems have succeeded in many computer vision tasks. However, it is found that the latest study indicates that these systems are in danger in the presence of adversarial attacks. These attacks can quickly spoil deep learning models, e.g., different convolutional neural networks (CNNs), used in various computer vision tasks from image classification to object detection. The adversarial examples are carefully designed by injecting a slight perturbation into the clean images. The proposed CRU-Net defense model is inspired by state-ofthe-art defense mechanisms such as MagNet defense, Generative Adversarial Network Defense, Deep Regret Analytic Generative Adversarial Networks Defense, Deep Denoising Sparse Autoencoder Defense, and Condtional Generattive Adversarial Network Defense. We have experimentally proved that our approach is better than previous defensive techniques. Our proposed CRU-Net model maps the adversarial image examples into clean images by eliminating the adversarial perturbation. The proposed defensive approach is based on residual and U-Net learning. Many experiments are done on the datasets MNIST and CIFAR10 to prove that our proposed CRU-Net defense model prevents adversarial example attacks in WhiteBox and BlackBox settings and improves the robustness of the deep learning algorithms especially in the computer vision field. We have also reported similarity (SSIM and PSNR) between the original and restored clean image examples by the proposed CRU-Net defense model.

show abstract

Section: Defense Methods Against Adversarial Attacksmentioning

confidence: 99%

“…These approaches are used after training target neural networks and adversarial attacks. For example, LID [31], Defense-GAN [32], MagNet [33], ComDefend [34], DRAGAN-Defense [35], DDSA-Defense [36], and cGan-Defense [37].…”

Section: Introductionmentioning

confidence: 99%

Defending Adversarial Examples by a Clipped Residual U-Net Model

Ali¹,

Qureshi²,

Bhatti³

et al. 2023

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

show abstract

“…However, the face restoration models also become susceptible to novel forms of security threats, e.g. adversarial attacks [14]- [16] and backdoor attacks [17]. Here for backdoor attacks, the output of the victim model can be controlled by adding the backdoor triggers or not.…”

Section: Introductionmentioning

confidence: 99%

FIBA: Frequency-Injection based Backdoor Attack in Medical Image Analysis

Feng

Zhang

et al. 2022

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

Deep learning-based face restoration models, increasingly prevalent in smart devices, have become targets for sophisticated backdoor attacks. These attacks, through subtle trigger injection into input face images, can lead to unexpected restoration outcomes. Unlike conventional methods focused on classification tasks, our approach introduces a unique degradation objective tailored for attacking restoration models. Moreover, we propose the Adaptive Selective Frequency Injection Backdoor Attack (AS-FIBA) framework, employing a neural network for input-specific trigger generation in the frequency domain, seamlessly blending triggers with benign images. This results in imperceptible yet effective attacks, guiding restoration predictions towards subtly degraded outputs rather than conspicuous targets. Extensive experiments demonstrate the efficacy of the degradation objective on state-of-the-art face restoration models. Additionally, it is notable that AS-FIBA can insert effective backdoors that are more imperceptible than existing backdoor attack methods, including WaNet, ISSBA, and FIBA.

show abstract