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

Edge-cloud collaborative inference empowers resource-limited IoT devices tosupport deep learning applications without disclosing their raw data to thecloud server, thus preserving privacy. Nevertheless, prior research has shownthat collaborative inference still results in the exposure of data andpredictions from edge devices. To enhance the privacy of collaborativeinference, we introduce a defense strategy called PrivaScissors, which isdesigned to reduce the mutual information between a model's intermediateoutcomes and the device's data and predictions. We evaluate PrivaScissors'sperformance on several datasets in the context of diverse attacks and offer atheoretical robustness guarantee.

PrivaScissors: Enhance the Privacy of Collaborative Inference through the Lens of Mutual Information