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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Deep learning architectures (DLA) have shown impressive performance incomputer vision, natural language processing and so on. Many DLA make use ofcloud computing to achieve classification due to the high computation andmemory requirements. Privacy and latency concerns resulting from cloudcomputing has inspired the deployment of DLA on embedded hardware accelerators.To achieve short time-to-market and have access to global experts,state-of-the-art techniques of DLA deployment on hardware accelerators areoutsourced to untrusted third parties. This outsourcing raises securityconcerns as hardware Trojans can be inserted into the hardware design of themapped DLA of the hardware accelerator. We argue that existing hardware Trojanattacks highlighted in literature have no qualitative means how definite theyare of the triggering of the Trojan. Also, most inserted Trojans show a obviousspike in the number of hardware resources utilized on the accelerator at thetime of triggering the Trojan or when the payload is active. In this paper, weintroduce a hardware Trojan attack called Input Interception Attack (IIA). Inthis attack, we make use of the statistical properties of layer-by-layer outputto ensure that asides from being stealthy. Our IIA is able to trigger with somemeasure of definiteness. Moreover, this IIA attack is tested on DLA used toclassify MNIST and Cifar-10 data sets. The attacked design utilizesapproximately up to 2% more LUTs respectively compared to the un-compromiseddesigns. Finally, this paper discusses potential defensive mechanisms thatcould be used to combat such hardware Trojans based attack in hardwareaccelerators for DLA.

A Stealthy Hardware Trojan Exploiting the Architectural Vulnerability of Deep Learning Architectures: Input Interception Attack (IIA)