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 classifiers are crucial in the age of artificial intelligence.The device-edge-based collaborative inference has been widely adopted as anefficient framework for promoting its applications in IoT and 5G/6G networks.However, it suffers from accuracy degradation under non-i.i.d. datadistribution and privacy disclosure. For accuracy degradation, direct use oftransfer learning and split learning is high cost and privacy issues remain.For privacy disclosure, cryptography-based approaches lead to a huge overhead.Other lightweight methods assume that the ground truth is non-sensitive and canbe exposed. But for many applications, the ground truth is the user's crucialprivacy-sensitive information. In this paper, we propose a framework ofRoulette, which is a task-oriented semantic privacy-preserving collaborativeinference framework for deep learning classifiers. More than input data, wetreat the ground truth of the data as private information. We develop a novelparadigm of split learning where the back-end DNN is frozen and the front-endDNN is retrained to be both a feature extractor and an encryptor. Moreover, weprovide a differential privacy guarantee and analyze the hardness of groundtruth inference attacks. To validate the proposed Roulette, we conductextensive performance evaluations using realistic datasets, which demonstratethat Roulette can effectively defend against various attacks and meanwhileachieve good model accuracy. In a situation where the non-i.i.d. is verysevere, Roulette improves the inference accuracy by 21\% averaged overbenchmarks, while making the accuracy of discrimination attacks almostequivalent to random guessing.

Roulette: A Semantic Privacy-Preserving Device-Edge Collaborative Inference Framework for Deep Learning Classification Tasks