Photonic-accelerated AI for cybersecurity in sustainable 6G networks DOI
Emilio Paolini, Luca Valcarenghi, Luca Maggiani

et al.

Published: June 6, 2023

The sixth generation (6G) of mobile communications, expected to be deployed around the year 2030, is predicted characterized by ubiquitous connected intelligence. With Artificial Intelligence (AI) operations being in every aspect future network infrastructure, security will also evolve from current solutions intelligent architectures. To meet massive amount computed AI models, photonic hardware can exploited, delivering higher processing speed and computing density lower power consumption with respect electronic counterparts. In this paper, we propose a photonic-based Convolutional Neural Network (CNN) solution able work on real-time traffic, capable identifying Denial Service (DoS) Hulk attacks 99.73 mean F1-score when exploiting 4 bits. We compared accelerators their counterparts, showing limited degradation, especially 8 bit scenarios.

Language: Английский

Residual based temporal attention convolutional neural network for detection of distributed denial of service attacks in software defined network integrated vehicular adhoc network DOI
V. C. Karthik,

R. Lakshmi,

Salini Abraham

et al.

International Journal of Network Management, Journal Year: 2023, Volume and Issue: 34(3)

Published: Dec. 6, 2023

Abstract Software defined network (SDN) integrated vehicular ad hoc (VANET) is a magnificent technique for smart transportation as it raises the efficiency, safety, manageability, and comfort of traffic. SDN‐integrated VANET (SDN‐int‐VANET) has numerous benefits, but susceptible to threats like distributed denial service (DDoS). Several methods were suggested DDoS attack detection (AD), existing approaches optimization have given base enhancing parameters. An incorrect selection parameters results in poor performance fit data. To overcome these issues, residual‐based temporal attention red fox‐convolutional neural (RTARF‐CNN) detecting attacks SDN‐int‐VANET introduced this manuscript. The input data taken from SDN dataset. For restoring redundancy missing value, developed random forest local least squares (DRFLLS) are applied. Then important features selected pre‐processed with help stacked contractive autoencoders (St‐CAE), which reduces processing time method. classified by attention‐convolutional (RTA‐CNN). weight parameter RTA‐CNN optimized fox (RFO) better classification. method implemented PYTHON platform. RTARF‐CNN attains 99.8% accuracy, 99.5% sensitivity, 99.80% precision, specificity. effectiveness compared approaches.

Language: Английский

Citations

1
uitSDD: Protect software defined networks from distributed denial-of-service using multi machine learning models DOI
Nguyen Tan Cam,

Tran Duc Viet

Cluster Computing, Journal Year: 2024, Volume and Issue: 28(1)

Published: Oct. 15, 2024

Language: Английский

Citations

0
An efficient framework for application layer DDoS attack detection and mitigation for Mobile Ad Hoc Network DOI Creative Commons
Kiran Salunke,

Suresh Kurumbanshi

Research Square (Research Square), Journal Year: 2023, Volume and Issue: unknown

Published: April 10, 2023

Abstract The authors have requested that this preprint be removed from Research Square.

Language: Английский

Citations

0
Photonic-accelerated AI for cybersecurity in sustainable 6G networks DOI
Emilio Paolini, Luca Valcarenghi, Luca Maggiani

et al.

Published: June 6, 2023

The sixth generation (6G) of mobile communications, expected to be deployed around the year 2030, is predicted characterized by ubiquitous connected intelligence. With Artificial Intelligence (AI) operations being in every aspect future network infrastructure, security will also evolve from current solutions intelligent architectures. To meet massive amount computed AI models, photonic hardware can exploited, delivering higher processing speed and computing density lower power consumption with respect electronic counterparts. In this paper, we propose a photonic-based Convolutional Neural Network (CNN) solution able work on real-time traffic, capable identifying Denial Service (DoS) Hulk attacks 99.73 mean F1-score when exploiting 4 bits. We compared accelerators their counterparts, showing limited degradation, especially 8 bit scenarios.

Language: Английский

Citations

0