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

We present a new method for black-box adversarial attack. Unlike previousmethods that combined transfer-based and scored-based methods by using thegradient or initialization of a surrogate white-box model, this new methodtries to learn a low-dimensional embedding using a pretrained model, and thenperforms efficient search within the embedding space to attack an unknowntarget network. The method produces adversarial perturbations with high levelsemantic patterns that are easily transferable. We show that this approach cangreatly improve the query efficiency of black-box adversarial attack acrossdifferent target network architectures. We evaluate our approach on MNIST,ImageNet and Google Cloud Vision API, resulting in a significant reduction onthe number of queries. We also attack adversarially defended networks onCIFAR10 and ImageNet, where our method not only reduces the number of queries,but also improves the attack success rate.

Black-Box Adversarial Attack with Transferable Model-based Embedding