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

Existing integrity verification approaches for deep models are designed forprivate verification (i.e., assuming the service provider is honest, withwhite-box access to model parameters). However, private verification approachesdo not allow model users to verify the model at run-time. Instead, they musttrust the service provider, who may tamper with the verification results. Incontrast, a public verification approach that considers the possibility ofdishonest service providers can benefit a wider range of users. In this paper,we propose PublicCheck, a practical public integrity verification solution forservices of run-time deep models. PublicCheck considers dishonest serviceproviders, and overcomes public verification challenges of being lightweight,providing anti-counterfeiting protection, and having fingerprinting samplesthat appear smooth. To capture and fingerprint the inherent predictionbehaviors of a run-time model, PublicCheck generates smoothly transformed andaugmented encysted samples that are enclosed around the model's decisionboundary while ensuring that the verification queries are indistinguishablefrom normal queries. PublicCheck is also applicable when knowledge of thetarget model is limited (e.g., with no knowledge of gradients or modelparameters). A thorough evaluation of PublicCheck demonstrates the strongcapability for model integrity breach detection (100% detection accuracy withless than 10 black-box API queries) against various model integrity attacks andmodel compression attacks. PublicCheck also demonstrates the smooth appearance,feasibility, and efficiency of generating a plethora of encysted samples forfingerprinting.

PublicCheck: Public Integrity Verification for Services of Run-time Deep Models