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

Neural networks are seeing increased use in diverse Internet of Things (IoT)applications such as healthcare, smart homes and industrial monitoring. Theirwidespread use makes neural networks a lucrative target for theft. An attackercan obtain a model without having access to the training data or incurring thecost of training. Also, networks trained using private data (e.g., medicalrecords) can reveal information about this data. Networks can be stolen byleveraging side channels such as power traces of the IoT device when it isrunning the network. Existing attacks require operations to occur in the sameorder each time; an attacker must collect and analyze several traces of thedevice to steal the network. Therefore, to prevent this type of attack, werandomly shuffle the order of operations each time. With shuffling, eachoperation can now happen at many different points in each execution, making theattack intractable. However, we show that shuffling in software can leakinformation which can be used to subvert this solution. Therefore, to performsecure shuffling and reduce latency, we present BlackJack, hardware added as afunctional unit within the CPU. BlackJack secures neural networks on IoTdevices by increasing the time needed for an attack to centuries, while addingjust 2.46% area, 3.28% power and 0.56% latency overhead on an ARM M0+ SoC.

BlackJack: Secure machine learning on IoT devices through hardware-based shuffling