Adversarial Attacks and Defense on Deep Learning Classification Models using YC<sub>b</sub>C<sub>r</sub> Color Images

Pestana, Camilo; Akhtar, Naveed; Liu, Wei; Glance, David; Mian, Ajmal

doi:10.1109/ijcnn52387.2021.9533495

Cited by 4 publications

(1 citation statement)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…No model has yet been able to resist adversarial perturbation while preserving state-of-the-art accuracy on clean inputs. However, several approaches to defending against small perturbations-based adversarial attacks and some novel training approaches have been proposed by researchers [14,15,[18][19][20][21][22][23][24][25][26]. Some of these works proposing methods to defend against adversarial attacks are briefly presented in the following.…”

Section: Related Workmentioning

confidence: 99%

Adversarial Attacks on Image Classification Models: FGSM and Patch Attacks and Their Impact

Sen¹,

Dasgupta²

2023

Information Security and Privacy in the Digital World - Some Selected Topics

View full text Add to dashboard Cite

This chapter introduces the concept of adversarial attacks on image classification models built on convolutional neural networks (CNN). CNNs are very popular deep-learning models which are used in image classification tasks. However, very powerful and pre-trained CNN models working very accurately on image datasets for image classification tasks may perform disastrously when the networks are under adversarial attacks. In this work, two very well-known adversarial attacks are discussed and their impact on the performance of image classifiers is analyzed. These two adversarial attacks are the fast gradient sign method (FGSM) and adversarial patch attack. These attacks are launched on three powerful pre-trained image classifier architectures, ResNet-34, GoogleNet, and DenseNet-161. The classification accuracy of the models in the absence and presence of the two attacks are computed on images from the publicly accessible ImageNet dataset. The results are analyzed to evaluate the impact of the attacks on the image classification task.

show abstract

Section: Related Workmentioning

confidence: 99%

Adversarial Attacks on Image Classification Models: FGSM and Patch Attacks and Their Impact

Sen¹,

Dasgupta²

2023

Information Security and Privacy in the Digital World - Some Selected Topics

View full text Add to dashboard Cite

show abstract

Adversarial Perturbations Straight on JPEG Coefficients

Sielmann,

Stelldinger

2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Defending CNN Against FGSM Attacks Using Beta-Based Personalized Activation Functions and Adversarial Training

Issaoui,

Eladel,

Zouinkhi

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Adversarial Attacks and Defense on Deep Learning Classification Models using YC_bC_r Color Images

Cited by 4 publications

References 24 publications

Adversarial Attacks on Image Classification Models: FGSM and Patch Attacks and Their Impact

Adversarial Attacks on Image Classification Models: FGSM and Patch Attacks and Their Impact

Adversarial Perturbations Straight on JPEG Coefficients

Defending CNN Against FGSM Attacks Using Beta-Based Personalized Activation Functions and Adversarial Training

Contact Info

Product

Resources

About

Adversarial Attacks and Defense on Deep Learning Classification Models using YCbCr Color Images

Cited by 4 publications

References 24 publications

Adversarial Attacks on Image Classification Models: FGSM and Patch Attacks and Their Impact

Adversarial Attacks on Image Classification Models: FGSM and Patch Attacks and Their Impact

Adversarial Perturbations Straight on JPEG Coefficients

Defending CNN Against FGSM Attacks Using Beta-Based Personalized Activation Functions and Adversarial Training

Contact Info

Product

Resources

About

Adversarial Attacks and Defense on Deep Learning Classification Models using YC_bC_r Color Images