Blockchain-based packet parser architecture for securing cyber-infrastructure and internet of things networks with auto-metric graph neural network
by R. Deepa; S. Subasree; N.K. Sakthivel; Amit Kumar Tyagi
International Journal of Mobile Communications (IJMC), Vol. 25, No. 2, 2025

Abstract: Blockchain technology, also known as cryptographic ledger technology, has recently been used to transport transactions and information securely through networks, primarily to increase security. AGNN long blockchain-based packet parser architecture is proposed for enabling cybersecurity at IoT devices. IoT architecture is processed on basis of three layers that are named as cloud layer, edge layer and device layer. Every node in edge layer is configured by proposed auto-metric graph neural network with BC-PP for analysing cyber-attacks. Proposed method is decentralised between edge nodes at edge layer of networks. Proposed technique will be executed on working platform of python device. Performance of proposed algorithm is evaluated under performance metrics, accuracy, detection time, attack probability, packet drop ratio, packet delivery ratio, computational time and delay. Here, proposed method provides 8.76%, 24.6%, 21.46% high accuracy, 69.53%, 45.5%, 66.7% lower detection time, 4.4%, 8.2%, 10% lower computation time comparing to existing methods, respectively.

Online publication date: Fri, 31-Jan-2025

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Mobile Communications (IJMC):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com