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

Deep neural networks (DNNs) are vulnerable to adversarial examples, which arecrafted by adding imperceptible perturbations to inputs. Recently differentattacks and strategies have been proposed, but how to generate adversarialexamples perceptually realistic and more efficiently remains unsolved. Thispaper proposes a novel framework called Attack-Inspired GAN (AI-GAN), where agenerator, a discriminator, and an attacker are trained jointly. Once trained,it can generate adversarial perturbations efficiently given input images andtarget classes. Through extensive experiments on several popular datasets \egMNIST and CIFAR-10, AI-GAN achieves high attack success rates and reducesgeneration time significantly in various settings. Moreover, for the firsttime, AI-GAN successfully scales to complicated datasets \eg CIFAR-100 witharound $90\%$ success rates among all classes.

AI-GAN: Attack-Inspired Generation of Adversarial Examples