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

Embedded devices are omnipresent in modern networks including the onesoperating inside critical environments. However, due to their constrainednature, novel mechanisms are required to provide external, and non-intrusiveanomaly detection. Among such approaches, one that has gained traction is basedon the analysis of the electromagnetic (EM) signals that get emanated during adevice's operation. However, one of the most neglected challenges of thisapproach is the requirement for manually gathering and fingerprinting thesignals that correspond to each execution path of the software/firmware.Indeed, even simple programs are comprised of hundreds if not thousands ofbranches thus, making the fingerprinting stage an extremely time-consumingprocess that involves the manual labor of a human specialist. To address thisissue, we propose a framework for generating synthetic EM signals directly fromthe machine code. The synthetic signals can be used to train a Machine Learningbased (ML) system for anomaly detection. The main advantage of the proposedapproach is that it completely removes the need for an elaborate anderror-prone fingerprinting stage, thus, dramatically increasing the scalabilityof the corresponding protection mechanisms. The experimental evaluationsindicate that our method provides high detection accuracy (above 90% AUC score)when employed for the detection of injection attacks. Moreover, the proposedmethodology inflicts only a small penalty (-1.3%) in accuracy for the detectionof the injection of as little as four malicious instructions when compared tothe same methods if real signals were to be used.

Towards Scalable EM-based Anomaly Detection For Embedded Devices Through Synthetic Fingerprinting