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

The intellectual property protection of deep learning (DL) models hasattracted increasing serious concerns. Many works on intellectual propertyprotection for Deep Neural Networks (DNN) models have been proposed. The vastmajority of existing work uses DNN watermarking to verify the ownership of themodel after piracy occurs, which is referred to as passive verification. On thecontrary, we focus on a new type of intellectual property protection methodnamed active copyright protection, which refers to active authorization controland user identity management of the DNN model. As of now, there is relativelylimited research in the field of active DNN copyright protection. In thisreview, we attempt to clearly elaborate on the connotation, attributes, andrequirements of active DNN copyright protection, provide evaluation methods andmetrics for active copyright protection, review and analyze existing work onactive DL model intellectual property protection, discuss potential attacksthat active DL model copyright protection techniques may face, and providechallenges and future directions for active DL model intellectual propertyprotection. This review is helpful to systematically introduce the new field ofactive DNN copyright protection and provide reference and foundation forsubsequent work.

Turn Passive to Active: A Survey on Active Intellectual Property Protection of Deep Learning Models