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

Model extraction attacks have been widely applied, which can normally be usedto recover confidential parameters of neural networks for multiple layers.Recently, side-channel analysis of neural networks allows parameter extractioneven for networks with several multiple deep layers with high effectiveness. Itis therefore of interest to implement a certain level of protection againstthese attacks. In this paper, we propose a desynchronization-basedcountermeasure that makes the timing analysis of activation functions harder.We analyze the timing properties of several activation functions and design thedesynchronization in a way that the dependency on the input and the activationtype is hidden. We experimentally verify the effectiveness of thecountermeasure on a 32-bit ARM Cortex-M4 microcontroller and employ a t-test toshow the side-channel information leakage. The overhead ultimately depends onthe number of neurons in the fully-connected layer, for example, in the case of4096 neurons in VGG-19, the overheads are between 2.8% and 11%.

A Desynchronization-Based Countermeasure Against Side-Channel Analysis of Neural Networks