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

The proliferation of the Internet of Things (IoT) has led to the emergence ofcrowdsensing applications, where a multitude of interconnected devicescollaboratively collect and analyze data. Ensuring the authenticity andintegrity of the data collected by these devices is crucial for reliabledecision-making and maintaining trust in the system. Traditional authenticationmethods are often vulnerable to attacks or can be easily duplicated, posingchallenges to securing crowdsensing applications. Besides, current solutionsleveraging device behavior are mostly focused on device identification, whichis a simpler task than authentication. To address these issues, an individualIoT device authentication framework based on hardware behavior fingerprintingand Transformer autoencoders is proposed in this work. This solution leveragesthe inherent imperfections and variations in IoT device hardware todifferentiate between devices with identical specifications. By monitoring andanalyzing the behavior of key hardware components, such as the CPU, GPU, RAM,and Storage on devices, unique fingerprints for each device are created. Theperformance samples are considered as time series data and used to trainoutlier detection transformer models, one per device and aiming to model itsnormal data distribution. Then, the framework is validated within a spectrumcrowdsensing system leveraging Raspberry Pi devices. After a pool ofexperiments, the model from each device is able to individually authenticate itbetween the 45 devices employed for validation. An average True Positive Rate(TPR) of 0.74+-0.13 and an average maximum False Positive Rate (FPR) of0.06+-0.09 demonstrate the effectiveness of this approach in enhancingauthentication, security, and trust in crowdsensing applications.

Single-board Device Individual Authentication based on Hardware Performance and Autoencoder Transformer Models