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

Distributed deep neural networks (DNNs) have been shown to reduce thecomputational burden of mobile devices and decrease the end-to-end inferencelatency in edge computing scenarios. While distributed DNNs have been studied,to the best of our knowledge, the resilience of distributed DNNs to adversarialaction remains an open problem. In this paper, we fill the existing researchgap by rigorously analyzing the robustness of distributed DNNs againstadversarial action. We cast this problem in the context of information theoryand rigorously proved that (i) the compressed latent dimension improves therobustness but also affect task-oriented performance; and (ii) the deepersplitting point enhances the robustness but also increases the computationalburden. These two trade-offs provide a novel perspective to design robustdistributed DNN. To test our theoretical findings, we perform extensiveexperimental analysis by considering 6 different DNN architectures, 6 differentapproaches for distributed DNN and 10 different adversarial attacks using theImageNet-1K dataset.

Adversarial Attacks to Latent Representations of Distributed Neural Networks in Split Computing