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

Deep learning has become popular, and numerous cloud-based services areprovided to help customers develop and deploy deep learning applications.Meanwhile, various attack techniques have also been discovered to stealthilycompromise the model's integrity. When a cloud customer deploys a deep learningmodel in the cloud and serves it to end-users, it is important for him to beable to verify that the deployed model has not been tampered with, and themodel's integrity is protected.  We propose a new low-cost and self-served methodology for customers to verifythat the model deployed in the cloud is intact, while having only black-boxaccess (e.g., via APIs) to the deployed model. Customers can detect arbitrarychanges to their deep learning models. Specifically, we define\texttt{Sensitive-Sample} fingerprints, which are a small set of transformedinputs that make the model outputs sensitive to the model's parameters. Evensmall weight changes can be clearly reflected in the model outputs, andobserved by the customer. Our experiments on different types of model integrityattacks show that we can detect model integrity breaches with high accuracy($>$99\%) and low overhead ($<$10 black-box model accesses).

VerIDeep: Verifying Integrity of Deep Neural Networks through Sensitive-Sample Fingerprinting