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 are quite vulnerable to adversarial perturbations.Current state-of-the-art adversarial attack methods typically require very timeconsuming hyper-parameter tuning, or require many iterations to solve anoptimization based adversarial attack. To address this problem, we present anew family of trust region based adversarial attacks, with the goal ofcomputing adversarial perturbations efficiently. We propose several attacksbased on variants of the trust region optimization method. We test the proposedmethods on Cifar-10 and ImageNet datasets using several different modelsincluding AlexNet, ResNet-50, VGG-16, and DenseNet-121 models. Our methodsachieve comparable results with the Carlini-Wagner (CW) attack, but withsignificant speed up of up to $37\times$, for the VGG-16 model on a Titan XpGPU. For the case of ResNet-50 on ImageNet, we can bring down itsclassification accuracy to less than 0.1\% with at most $1.5\%$ relative$L_\infty$ (or $L_2$) perturbation requiring only $1.02$ seconds as compared to$27.04$ seconds for the CW attack. We have open sourced our method which can beaccessed at [1].

Trust Region Based Adversarial Attack on Neural Networks