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/

Zendy Plus

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

Zendy Tools

Zendy Open

A new collaborative learning, called split learning, was recently introduced,aiming to protect user data privacy without revealing raw input data to aserver. It collaboratively runs a deep neural network model where the model issplit into two parts, one for the client and the other for the server.Therefore, the server has no direct access to raw data processed at the client.Until now, the split learning is believed to be a promising approach to protectthe client's raw data; for example, the client's data was protected inhealthcare image applications using 2D convolutional neural network (CNN)models. However, it is still unclear whether the split learning can be appliedto other deep learning models, in particular, 1D CNN.  In this paper, we examine whether split learning can be used to performprivacy-preserving training for 1D CNN models. To answer this, we first designand implement an 1D CNN model under split learning and validate its efficacy indetecting heart abnormalities using medical ECG data. We observed that the 1DCNN model under split learning can achieve the same accuracy of 98.9\% like theoriginal (non-split) model. However, our evaluation demonstrates that splitlearning may fail to protect the raw data privacy on 1D CNN models. To addressthe observed privacy leakage in split learning, we adopt two privacy leakagemitigation techniques: 1) adding more hidden layers to the client side and 2)applying differential privacy. Although those mitigation techniques are helpfulin reducing privacy leakage, they have a significant impact on model accuracy.Hence, based on those results, we conclude that split learning alone would notbe sufficient to maintain the confidentiality of raw sequential data in 1D CNNmodels.

Can We Use Split Learning on 1D CNN Models for Privacy Preserving Training?