Leveraging self attention driven gated recurrent unit with crocodile optimization algorithm for cyberattack detection using federated learning framework

Abstract Cybersecurity has been defined as a vital part of the developments, which is mainly related to technology. Enlarged cybersecurity safeguards that the data remains safe. Cyberattacks like computer malware, denial-of-service (DoS) attacks, or unauthorized access led to severe damage and econo...

Full description

Saved in:
Bibliographic Details
Main Authors: Manal Abdullah Alohali, Hatim Dafaalla, Mohammed Baihan, Sultan Alahmari, Achraf Ben Miled, Othman Alrusaini, Ali Alqazzaz, Hanadi Alkhudhayr
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-99452-4
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849399654898204672
author Manal Abdullah Alohali
Hatim Dafaalla
Mohammed Baihan
Sultan Alahmari
Achraf Ben Miled
Othman Alrusaini
Ali Alqazzaz
Hanadi Alkhudhayr
author_facet Manal Abdullah Alohali
Hatim Dafaalla
Mohammed Baihan
Sultan Alahmari
Achraf Ben Miled
Othman Alrusaini
Ali Alqazzaz
Hanadi Alkhudhayr
author_sort Manal Abdullah Alohali
collection DOAJ
description Abstract Cybersecurity has been defined as a vital part of the developments, which is mainly related to technology. Enlarged cybersecurity safeguards that the data remains safe. Cyberattacks like computer malware, denial-of-service (DoS) attacks, or unauthorized access led to severe damage and economic losses in large-scale systems. Cybersecurity includes decreasing the risk of mischievous computer, software, and network attacks. Novel techniques have been combined into emerging artificial intelligence (AI) that attains cybersecurity. ML is usually reflected as a sub-branch of AI, which is closely linked to data mining, computational statistics, and data science (DS) and mainly concentrates on generating computers to acquire data. Federated learning (FL) is one of the ML models that permits tackling cyberattack issues like security, data privacy, and access rights. This study proposes a Self-Attention Mechanism-Driven Federated Learning for Secure Cyberattack Detection with Crocodile Optimization Algorithm (SAMFL-SCDCOA) methodology. The main objective of the SAMFL-SCDCOA methodology is to provide an effective method for preventing cyberattacks in real time using FL and advanced optimization algorithms. Initially, the Z-score normalization is utilized to scale and standardize data to improve analysis consistency and accuracy. Furthermore, the feature selection (FS) process uses the crocodile optimization algorithm (COA) model. The proposed SAMFL-SCDCOA approach employs the gated recurrent unit with a self-attention (GRU-SA) model for the cybersecurity classification. Finally, the improved pelican optimization algorithm (IPOA) optimally adjusts the hyperparameter values of the GRU-SA model, leading to enhanced classification performance. A wide range of experiments has been accomplished to validate the performance of the SAMFL-SCDCOA technique under the CICIDS-2017 dataset. The comparison study of the SAMFL-SCDCOA technique emphasized a superior output of 99.04% over existing models.
format Article
id doaj-art-a9b11c0293cd43199cbf72a4c2d6e591
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-a9b11c0293cd43199cbf72a4c2d6e5912025-08-20T03:38:16ZengNature PortfolioScientific Reports2045-23222025-07-0115112310.1038/s41598-025-99452-4Leveraging self attention driven gated recurrent unit with crocodile optimization algorithm for cyberattack detection using federated learning frameworkManal Abdullah Alohali0Hatim Dafaalla1Mohammed Baihan2Sultan Alahmari3Achraf Ben Miled4Othman Alrusaini5Ali Alqazzaz6Hanadi Alkhudhayr7Department of Information Systems, College of Computer and Information Sciences, Princess Nourah Bint Abdulrahman UniversityDepartment of Computer Science, Applied College at Mahayil, King Khalid UniversityDepartment of Computer Science, Community College, King Saud UniversityKing Abdul Aziz City for Science and Technology (KACST), Cybersecurity InstituteDepartment of Computer Science, College of Science, Northern Border UniversityDepartment of Engineering and Applied Sciences, Applied College, Umm Al-Qura University Department of Computer Science and Artificial Intelligence, College of Computing and Information Technology, University of BishaDepartment of Information Systems, Faculty of Computing and Information Technology, King Abdulaziz UniversityAbstract Cybersecurity has been defined as a vital part of the developments, which is mainly related to technology. Enlarged cybersecurity safeguards that the data remains safe. Cyberattacks like computer malware, denial-of-service (DoS) attacks, or unauthorized access led to severe damage and economic losses in large-scale systems. Cybersecurity includes decreasing the risk of mischievous computer, software, and network attacks. Novel techniques have been combined into emerging artificial intelligence (AI) that attains cybersecurity. ML is usually reflected as a sub-branch of AI, which is closely linked to data mining, computational statistics, and data science (DS) and mainly concentrates on generating computers to acquire data. Federated learning (FL) is one of the ML models that permits tackling cyberattack issues like security, data privacy, and access rights. This study proposes a Self-Attention Mechanism-Driven Federated Learning for Secure Cyberattack Detection with Crocodile Optimization Algorithm (SAMFL-SCDCOA) methodology. The main objective of the SAMFL-SCDCOA methodology is to provide an effective method for preventing cyberattacks in real time using FL and advanced optimization algorithms. Initially, the Z-score normalization is utilized to scale and standardize data to improve analysis consistency and accuracy. Furthermore, the feature selection (FS) process uses the crocodile optimization algorithm (COA) model. The proposed SAMFL-SCDCOA approach employs the gated recurrent unit with a self-attention (GRU-SA) model for the cybersecurity classification. Finally, the improved pelican optimization algorithm (IPOA) optimally adjusts the hyperparameter values of the GRU-SA model, leading to enhanced classification performance. A wide range of experiments has been accomplished to validate the performance of the SAMFL-SCDCOA technique under the CICIDS-2017 dataset. The comparison study of the SAMFL-SCDCOA technique emphasized a superior output of 99.04% over existing models.https://doi.org/10.1038/s41598-025-99452-4Self-attention mechanismFederated learningCyberattack detectionCrocodile optimization algorithmCybersecurity
spellingShingle Manal Abdullah Alohali
Hatim Dafaalla
Mohammed Baihan
Sultan Alahmari
Achraf Ben Miled
Othman Alrusaini
Ali Alqazzaz
Hanadi Alkhudhayr
Leveraging self attention driven gated recurrent unit with crocodile optimization algorithm for cyberattack detection using federated learning framework
Scientific Reports
Self-attention mechanism
Federated learning
Cyberattack detection
Crocodile optimization algorithm
Cybersecurity
title Leveraging self attention driven gated recurrent unit with crocodile optimization algorithm for cyberattack detection using federated learning framework
title_full Leveraging self attention driven gated recurrent unit with crocodile optimization algorithm for cyberattack detection using federated learning framework
title_fullStr Leveraging self attention driven gated recurrent unit with crocodile optimization algorithm for cyberattack detection using federated learning framework
title_full_unstemmed Leveraging self attention driven gated recurrent unit with crocodile optimization algorithm for cyberattack detection using federated learning framework
title_short Leveraging self attention driven gated recurrent unit with crocodile optimization algorithm for cyberattack detection using federated learning framework
title_sort leveraging self attention driven gated recurrent unit with crocodile optimization algorithm for cyberattack detection using federated learning framework
topic Self-attention mechanism
Federated learning
Cyberattack detection
Crocodile optimization algorithm
Cybersecurity
url https://doi.org/10.1038/s41598-025-99452-4
work_keys_str_mv AT manalabdullahalohali leveragingselfattentiondrivengatedrecurrentunitwithcrocodileoptimizationalgorithmforcyberattackdetectionusingfederatedlearningframework
AT hatimdafaalla leveragingselfattentiondrivengatedrecurrentunitwithcrocodileoptimizationalgorithmforcyberattackdetectionusingfederatedlearningframework
AT mohammedbaihan leveragingselfattentiondrivengatedrecurrentunitwithcrocodileoptimizationalgorithmforcyberattackdetectionusingfederatedlearningframework
AT sultanalahmari leveragingselfattentiondrivengatedrecurrentunitwithcrocodileoptimizationalgorithmforcyberattackdetectionusingfederatedlearningframework
AT achrafbenmiled leveragingselfattentiondrivengatedrecurrentunitwithcrocodileoptimizationalgorithmforcyberattackdetectionusingfederatedlearningframework
AT othmanalrusaini leveragingselfattentiondrivengatedrecurrentunitwithcrocodileoptimizationalgorithmforcyberattackdetectionusingfederatedlearningframework
AT alialqazzaz leveragingselfattentiondrivengatedrecurrentunitwithcrocodileoptimizationalgorithmforcyberattackdetectionusingfederatedlearningframework
AT hanadialkhudhayr leveragingselfattentiondrivengatedrecurrentunitwithcrocodileoptimizationalgorithmforcyberattackdetectionusingfederatedlearningframework