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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Deep Neural Networks (DNNs) are well-known to be vulnerable to AdversarialExamples (AEs). A large amount of efforts have been spent to launch and heatthe arms race between the attackers and defenders. Recently, advancedgradient-based attack techniques were proposed (e.g., BPDA and EOT), which havedefeated a considerable number of existing defense methods. Up to today, thereare still no satisfactory solutions that can effectively and efficiently defendagainst those attacks.  In this paper, we make a steady step towards mitigating those advancedgradient-based attacks with two major contributions. First, we perform anin-depth analysis about the root causes of those attacks, and propose fourproperties that can break the fundamental assumptions of those attacks. Second,we identify a set of operations that can meet those properties. By integratingthese operations, we design two preprocessing functions that can invalidatethese powerful attacks. Extensive evaluations indicate that our solutions caneffectively mitigate all existing standard and advanced attack techniques, andbeat 11 state-of-the-art defense solutions published in top-tier conferencesover the past 2 years. The defender can employ our solutions to constrain theattack success rate below 7% for the strongest attacks even the adversary hasspent dozens of GPU hours.

Mitigating Advanced Adversarial Attacks with More Advanced Gradient Obfuscation Techniques