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 (DL) techniques allow ones to train models from a dataset tosolve tasks. DL has attracted much interest given its fancy performance andpotential market value, while security issues are amongst the most colossalconcerns. However, the DL models may be prone to the membership inferenceattack, where an attacker determines whether a given sample is from thetraining dataset. Efforts have been made to hinder the attack butunfortunately, they may lead to a major overhead or impaired usability. In thispaper, we propose and implement DAMIA, leveraging Domain Adaptation (DA) as adefense aginist membership inference attacks. Our observation is that duringthe training process, DA obfuscates the dataset to be protected using anotherrelated dataset, and derives a model that underlyingly extracts the featuresfrom both datasets. Seeing that the model is obfuscated, membership inferencefails, while the extracted features provide supports for usability. Extensiveexperiments have been conducted to validates our intuition. The model trainedby DAMIA has a negligible footprint to the usability. Our experiment alsoexcludes factors that may hinder the performance of DAMIA, providing apotential guideline to vendors and researchers to benefit from our solution ina timely manner.

DAMIA: Leveraging Domain Adaptation as a Defense against Membership Inference Attacks