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 zaia usage as premium feature

ZAIA

Presents the pdf analysis as premium feature

PDF Analysis

Insights

Presents the summarisation as premium feature

Summarisation

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the access of premium content as premium feature

Premium Content

Zendy Tools

Zendy Open

The connectivity and resource-constrained nature of single-board devices openthe door to cybersecurity concerns affecting Internet of Things (IoT)scenarios. One of the most important issues is the presence of unauthorized IoTdevices that want to impersonate legitimate ones by using identical hardwareand software specifications. This situation can provoke sensitive informationleakages, data poisoning, or privilege escalation in IoT scenarios. Combiningbehavioral fingerprinting and Machine/Deep Learning (ML/DL) techniques is apromising approach to identify these malicious spoofing devices by detectingminor performance differences generated by imperfections in manufacturing.However, existing solutions are not suitable for single-board devices sincethey do not consider their hardware and software limitations, underestimatecritical aspects such as fingerprint stability or context changes, and do notexplore the potential of ML/DL techniques. To improve it, this work firstidentifies the essential properties for single-board device identification:uniqueness, stability, diversity, scalability, efficiency, robustness, andsecurity. Then, a novel methodology relies on behavioral fingerprinting toidentify identical single-board devices and meet the previous properties. Themethodology leverages the different built-in components of the system and ML/DLtechniques, comparing the device internal behavior with each other to detectmanufacturing variations. The methodology validation has been performed in areal environment composed of 15 identical Raspberry Pi 4 B and 10 Raspberry Pi3 B+ devices, obtaining a 91.9% average TPR and identifying all devices bysetting a 50% threshold in the evaluation process. Finally, a discussioncompares the proposed solution with related work, highlighting the fingerprintproperties not met, and provides important lessons learned and limitations.

A methodology to identify identical single-board computers based on hardware behavior fingerprinting