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

Fine-tuning is a prominent technique to adapt a pre-trained language model todownstream scenarios. In parameter-efficient fine-tuning, only a small subsetof modules are trained over the downstream datasets, while leaving the rest ofthe pre-trained model frozen to save computation resources. In recent years, apopular productization form arises as Model-as-a-Service (MaaS), in whichvendors provide abundant pre-trained language models, server resources and corefunctions, and customers can fine-tune, deploy and invoke their customizedmodel by accessing the one-stop MaaS with their own private dataset. In thispaper, we identify the model and data privacy leakage risks in MaaSfine-tuning, and propose a Split-and-Privatize (SAP) framework, which manage tomitigate the privacy issues by adapting the existing split learningarchitecture. The proposed SAP framework is sufficiently investigated byexperiments, and the results indicate that it can enhance the empirical privacyby 62% at the cost of 1% model performance degradation on the StanfordSentiment Treebank dataset.

A Split-and-Privatize Framework for Large Language Model Fine-Tuning