LDSAE: LeNet deep stacked autoencoder for secure systems to mitigate the errors of jamming attacks in cognitive radio networks

Chandrakant Athavale Chhaya and K.P. Patil

International Journal of Networking and Virtual Organisations, 2024, vol. 31, issue 2, 127-146

Abstract: A hybrid network system for mitigating errors due to jamming attacks in cognitive radio networks (CRNs) is named LeNet deep stacked autoencoder (LDSAE) and is developed. In this exploration, the sensing stage and decision-making are considered. The sensing unit is composed of four steps. First, the detected signal is forwarded to filtering progression. Here, BPF is utilised to filter the detected signal. The filtered signal is squared in the second phase. Third, signal samples are combined and jamming attacks occur by including false energy levels. Last, the attack is maliciously affecting the FC decision in the fourth step. On the other hand, FC initiated the decision-making and also recognised jamming attacks that affect the link amidst PU and SN in decision-making stage and it is accomplished by employing LDSAE-based trust model where the proposed module differentiates the malicious and selfish users. The analytic measures of LDSAE gained 79.40%, 79.90%, and 78.40%.

Keywords: CRNs; cognitive radio networks; FC; fusion center; band pass filter; LeNet; DSAE; deep stacked auto encoder. (search for similar items in EconPapers)
Date: 2024
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.inderscience.com/link.php?id=142242 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ids:ijnvor:v:31:y:2024:i:2:p:127-146

Access Statistics for this article

More articles in International Journal of Networking and Virtual Organisations from Inderscience Enterprises Ltd
Bibliographic data for series maintained by Sarah Parker ().