English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The notion of adversarial attacks on image classification models based onconvolutional neural networks (CNN) is introduced in this work. To classifyimages, deep learning models called CNNs are frequently used. However, when thenetworks are subject to adversarial attacks, extremely potent and previouslytrained CNN models that perform quite effectively on image datasets for imageclassification tasks may perform poorly. In this work, one well-knownadversarial attack known as the fast gradient sign method (FGSM) is exploredand its adverse effects on the performances of image classification models areexamined. The FGSM attack is simulated on three pre-trained image classifierCNN architectures, ResNet-101, AlexNet, and RegNetY 400MF using randomly chosenimages from the ImageNet dataset. The classification accuracies of the modelsare computed in the absence and presence of the attack to demonstrate thedetrimental effect of the attack on the performances of the classifiers.Finally, a mechanism is proposed to defend against the FGSM attack based on amodified defensive distillation-based approach. Extensive results are presentedfor the validation of the proposed scheme.

Adversarial Attacks on Image Classification Models: Analysis and Defense