Defending against adversarial attacks on Covid-19 classifier: A denoiser-based approach

Kansal, Keshav; Krishna, P. Sai; Jain, Parshva  B.; Surya, R; Honnavalli, Prasad B; Eswaran, Sivaraman

doi:10.1016/j.heliyon.2022.e11209

Cited by 10 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In general, adversarial training improves deep neural networks' (DNNs') intrinsic robustness without adding any extraneous parts, while preserving its ability to make accurate inferences from valid data. Different protection strategies focus on pre-processing data (both clean and hostile instances) without influencing later computer-aided analysis networks, strengthening the intrinsic network resistance against adversarial components [20,46]. In simple terms, the data pre-processing aims to retain the original form of clean inputs while converting hostile samples into benign equivalents for future inference.…”

Section: Medical Image Analysismentioning

confidence: 99%

“…Furthermore, a comprehensive metric is proposed to determine the confidence level of MedRDF diagnosis, aiding healthcare professionals in their clinical practice. Kansal et al [46] expanded upon the High-level representation Guided Denoiser (HGD) [118] to defend medical picture applications against hostile examples in both white-box and black-box scenarios instead of focusing just on pixel-level denoising. The incorporation of high-level information can enhance the process of eliminating the adversarial effect at the image level, leading to a more accurate final diagnosis without causing visual disruption.…”

Section: Image Level Preprocessingmentioning

confidence: 99%

See 1 more Smart Citation

A Comprehensive Review and Analysis of Deep Learning-Based Medical Image Adversarial Attack and Defense

Muoka,

Yi,

Ukwuoma

et al. 2023

Mathematics

View full text Add to dashboard Cite

Deep learning approaches have demonstrated great achievements in the field of computer-aided medical image analysis, improving the precision of diagnosis across a range of medical disorders. These developments have not, however, been immune to the appearance of adversarial attacks, creating the possibility of incorrect diagnosis with substantial clinical implications. Concurrently, the field has seen notable advancements in defending against such targeted adversary intrusions in deep medical diagnostic systems. In the context of medical image analysis, this article provides a comprehensive survey of current advancements in adversarial attacks and their accompanying defensive strategies. In addition, a comprehensive conceptual analysis is presented, including several adversarial attacks and defensive strategies designed for the interpretation of medical images. This survey, which draws on qualitative and quantitative findings, concludes with a thorough discussion of the problems with adversarial attack and defensive mechanisms that are unique to medical image analysis systems, opening up new directions for future research. We identified that the main problems with adversarial attack and defense in medical imaging include dataset and labeling, computational resources, robustness against target attacks, evaluation of transferability and adaptability, interpretability and explainability, real-time detection and response, and adversarial attacks in multi-modal fusion. The area of medical imaging adversarial attack and defensive mechanisms might move toward more secure, dependable, and therapeutically useful deep learning systems by filling in these research gaps and following these future objectives.

show abstract

Section: Medical Image Analysismentioning

confidence: 99%

Section: Image Level Preprocessingmentioning

confidence: 99%

A Comprehensive Review and Analysis of Deep Learning-Based Medical Image Adversarial Attack and Defense

Muoka,

Yi,

Ukwuoma

et al. 2023

Mathematics

View full text Add to dashboard Cite

show abstract

“…While several researchers have focused on image-based AE, audio and speech-based AE are gaining popularity. In the work, [11], the adversarial robustness of such Covid-19 classifiers has been proposed using common adversarial attacks, such as Fast Gradient Sign Method (FGSM) and Projected Gradient Descent (PGD).…”

Section: Introductionmentioning

confidence: 99%

Secure Convolutional Neural Network-Based Internet-of-Healthcare Applications

et al. 2023

View full text Add to dashboard Cite

Convolutional Neural Networks (CNNs) have gained popularity for Internet-of-Healthcare (IoH) applications such as medical diagnostics. However, new research shows that adversarial attacks with slight imperceptible changes can undermine deep neural network techniques in healthcare. This raises questions regarding the safety of deploying these IoH devices in clinical situations. In this paper, we review the techniques used in fighting against cyber-attacks. Then, we propose to study the robustness of some well-known CNN architectures' belonging to sequential, parallel, and residual families, such as LeNet5, MobileNetV1, VGG16, ResNet50, and InceptionV3 against Fast Gradient Sign Method (FGSM) and Projected Gradient Descent (PGD) attacks, in the context of classification of chest radiographs (Xrays) based on the IoH application. Finally, we propose to improve the security of these CNN structures by studying standard and adversarial training. The results show that, among these models, smaller models with lower computational complexity are more secure against hostile threats than larger models that are frequently used in IoH applications. In contrast, we reveal that when these networks are learned adversarially, they can outperform standard trained networks. The experimental results demonstrate that the model performance breakpoint is represented by γ = 0.3 with a maximum loss of accuracy tolerated at 2%.

show abstract

Improving adversarial robustness of medical imaging systems via adding global attention noise

Dai

Qian

Liu

et al. 2023

Computers in Biology and Medicine

View full text Add to dashboard Cite

Defending against adversarial attacks on Covid-19 classifier: A denoiser-based approach

Cited by 10 publications

References 16 publications

A Comprehensive Review and Analysis of Deep Learning-Based Medical Image Adversarial Attack and Defense

A Comprehensive Review and Analysis of Deep Learning-Based Medical Image Adversarial Attack and Defense

Secure Convolutional Neural Network-Based Internet-of-Healthcare Applications

Improving adversarial robustness of medical imaging systems via adding global attention noise

Contact Info

Product

Resources

About