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/

Zendy Plus

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

Zendy Tools

Zendy Open

Transfer-based adversarial attacks can evaluate model robustness in theblack-box setting. Several methods have demonstrated impressive untargetedtransferability, however, it is still challenging to efficiently producetargeted transferability. To this end, we develop a simple yet effectiveframework to craft targeted transfer-based adversarial examples, applying ahierarchical generative network. In particular, we contribute to amortizeddesigns that well adapt to multi-class targeted attacks. Extensive experimentson ImageNet show that our method improves the success rates of targetedblack-box attacks by a significant margin over the existing methods -- itreaches an average success rate of 29.1\% against six diverse models based onlyon one substitute white-box model, which significantly outperforms thestate-of-the-art gradient-based attack methods. Moreover, the proposed methodis also more efficient beyond an order of magnitude than gradient-basedmethods.

Boosting Transferability of Targeted Adversarial Examples via Hierarchical Generative Networks