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

Malicious intelligent algorithms greatly threaten the security of socialusers' privacy by detecting and analyzing the uploaded photos to social networkplatforms. The destruction to DNNs brought by the adversarial attack sparks thepotential that adversarial examples serve as a new protection mechanism forprivacy security in social networks. However, the existing adversarial exampledoes not have recoverability for serving as an effective protection mechanism.To address this issue, we propose a recoverable generative adversarial networkto generate self-recoverable adversarial examples. By modeling the adversarialattack and recovery as a united task, our method can minimize the error of therecovered examples while maximizing the attack ability, resulting in betterrecoverability of adversarial examples. To further boost the recoverability ofthese examples, we exploit a dimension reducer to optimize the distribution ofadversarial perturbation. The experimental results prove that the adversarialexamples generated by the proposed method present superior recoverability,attack ability, and robustness on different datasets and network architectures,which ensure its effectiveness as a protection mechanism in social networks.

Self-recoverable Adversarial Examples: A New Effective Protection Mechanism in Social Networks