Hybridization of synergistic swarm and differential evolution with graph convolutional network for distributed denial of service detection and mitigation in IoT environment DOI Creative Commons

C. Naveeth Babu,

Suneetha Manne, Mohammed Altaf Ahmed

et al.

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Dec. 28, 2024

Enhanced technologies of the future are gradually improving digital landscape. Internet Things (IoT) technology is an advanced technique that quickly increasing owing to development a network organized online devices. In today's era, IoT considered one most robust technologies. However, attackers can effortlessly hack devices employed generate botnets, and it applied present distributed denial service (DDoS) attacks beside networks. The DDoS attack foremost on system causes complete go down. Thus, average consumers may need help get services they from server. compromised or want be perceived well in system. So, presently, Deep Learning (DL) plays prominent part forecasting end-users' behaviour by extracting features identifying adversary network. This paper proposes Synergistic Swarm Optimization Differential Evolution with Graph Convolutional Network Cyberattack Detection Mitigation (SSODE-GCNDM) environment. main intention SSODE-GCNDM method recognize presence platforms. Primarily, utilizes Z-score normalization scale input data into uniform format. presented approach synergistic swarm optimization differential evolution (SSO-DE) for feature selection. Moreover, graph convolutional (GCN) recognizes mitigates attacks. Finally, implements northern goshawk (NGO) fine-tune hyperparameters involved GCN method. An extensive range experimentation analyses occur, outcomes observed using numerous features. experimental validation portrayed superior accuracy value 99.62% compared existing approaches.

Language: Английский

Secured DDoS Attack Detection in SDN Using TS‐RBDM With MDPP‐Streebog Based User Authentication DOI Open Access
Monika Dandotiya, Rajni Ranjan Singh Makwana

Transactions on Emerging Telecommunications Technologies, Journal Year: 2025, Volume and Issue: 36(2)

Published: Jan. 23, 2025

ABSTRACT In a Distributed Denial of Service (DDoS) attack, the attacker aims to render network resource unavailable its intended users. A novel Software Defined Networking (SDN)‐centered secured DDoS attack detection system is presented in this paper by utilizing TanhSoftmax‐Restricted Boltzmann Dense Machines (TS‐RBDM) with Mean Difference Public key and Private based Streebog (MDPP‐Streebog) user authentication algorithm. Primarily, registration phase, users have registered their device details. The two‐stage login process performed after successful registration. Then, layer, nodes are initialized, via Gate/Router, sensed data transmitted SDN controller enhance energy efficiency. Later, using CIC 2019 dataset, trained. This dataset undergoes preprocessing, features extracted from it. By employing Adaptive Synthetic (ADASYN) technique, balancing achieved. Lastly, TS‐RBDM categorized as either attacked or non‐attacked within trained system. Entropy Binomial probability‐based Shanon‐Fano‐Elias (EB‐SFE) will be encoded receiving terminal. experiential assessment illustrated that proposed attained 98% accuracy 37 485 ms minimal training time, thus outperforming all state‐of‐the‐art methods.

Language: Английский

Citations

0
SA-IDS: A single attribute intrusion detection system for Slow DoS attacks in IoT networks DOI Creative Commons
Andy Reed,

Laurence S. Dooley,

Soraya Kouadri Mostéfaoui

et al.

Internet of Things, Journal Year: 2025, Volume and Issue: 30, P. 101512 - 101512

Published: Feb. 7, 2025

Language: Английский

Citations

0
Towards Robust SDN Security: A Comparative Analysis of Oversampling Techniques with ML and DL Classifiers DOI Open Access

Aboubakr Salem Bajenaid,

Maher Khemakhem, Fathy Eassa

et al.

Electronics, Journal Year: 2025, Volume and Issue: 14(5), P. 995 - 995

Published: Feb. 28, 2025

Software-defined networking (SDN) is becoming a predominant architecture for managing diverse networks. However, recent research has exhibited the susceptibility of SDN architectures to cyberattacks, which increases its security challenges. Many researchers have used machine learning (ML) and deep (DL) classifiers mitigate cyberattacks in architectures. Since datasets could suffer from class imbalance issues, classification accuracy predictive undermined. Therefore, this conducts comparative analysis impact utilizing oversampling principal component (PCA) techniques on ML DL using publicly available datasets. This approach combines mitigating issue maintaining effectiveness performance when reducing data dimensionality. Initially, are balance classes Then, evaluated compared observe each technique classifier. PCA applied balanced dataset, classifier’s compared. The results demonstrated that Random Oversampling outperformed other balancing techniques. Furthermore, XGBoost Transformer were most sensitive models algorithms. In addition, macro weighted averages evaluation metrics calculated show imbalanced

Language: Английский

Citations

0
The Guardian Node Slow DoS Detection Model for Real-Time Application in IoT Networks DOI Creative Commons
Andy Reed,

Laurence S. Dooley,

Soraya Kouadri Mostéfaoui

et al.

Sensors, Journal Year: 2024, Volume and Issue: 24(17), P. 5581 - 5581

Published: Aug. 28, 2024

The pernicious impact of malicious Slow DoS (Denial Service) attacks on the application layer and web-based Open Systems Interconnection model services like

Language: Английский

Citations

1
Deep learning approaches for protecting IoT devices in smart homes from MitM attacks DOI Creative Commons

Nader Karmous,

Yassmine Ben Dhiab, Mohamed Ould-Elhassen Aoueileyine

et al.

Frontiers in Computer Science, Journal Year: 2024, Volume and Issue: 6

Published: Oct. 30, 2024

The primary objective of this paper is to enhance the security IoT devices in Software-Defined Networking (SDN) environments against Man-in-the-Middle (MitM) attacks smart homes using Artificial Intelligence (AI) methods as part an Intrusion Detection and Prevention System (IDPS) framework. This framework aims authenticate communication parties, ensure overall system network within SDN environments, foster trust among users stakeholders. experimental analysis focuses on machine learning (ML) deep (DL) algorithms, particularly those employed Systems (IDS), such Naive Bayes (NB), k-Nearest Neighbors (kNN), Random Forest (RF), Convolutional Neural Networks (CNN). CNN algorithm demonstrates exceptional performance training dataset, achieving 99.96% accuracy with minimal time. It also shows favorable results terms detection speed, requiring only 1 s, maintains a low False Alarm Rate (FAR) 0.02%. Subsequently, proposed was deployed testbed environment evaluate its capabilities across diverse topologies, showcasing efficiency compared existing approaches.

Language: Английский

Citations

0
Hybridization of synergistic swarm and differential evolution with graph convolutional network for distributed denial of service detection and mitigation in IoT environment DOI Creative Commons

C. Naveeth Babu,

Suneetha Manne, Mohammed Altaf Ahmed

et al.

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Dec. 28, 2024

Enhanced technologies of the future are gradually improving digital landscape. Internet Things (IoT) technology is an advanced technique that quickly increasing owing to development a network organized online devices. In today's era, IoT considered one most robust technologies. However, attackers can effortlessly hack devices employed generate botnets, and it applied present distributed denial service (DDoS) attacks beside networks. The DDoS attack foremost on system causes complete go down. Thus, average consumers may need help get services they from server. compromised or want be perceived well in system. So, presently, Deep Learning (DL) plays prominent part forecasting end-users' behaviour by extracting features identifying adversary network. This paper proposes Synergistic Swarm Optimization Differential Evolution with Graph Convolutional Network Cyberattack Detection Mitigation (SSODE-GCNDM) environment. main intention SSODE-GCNDM method recognize presence platforms. Primarily, utilizes Z-score normalization scale input data into uniform format. presented approach synergistic swarm optimization differential evolution (SSO-DE) for feature selection. Moreover, graph convolutional (GCN) recognizes mitigates attacks. Finally, implements northern goshawk (NGO) fine-tune hyperparameters involved GCN method. An extensive range experimentation analyses occur, outcomes observed using numerous features. experimental validation portrayed superior accuracy value 99.62% compared existing approaches.

Language: Английский

Citations

0