Machine learning based detection of DDoS attacks in software defined network

Kannan, Charulatha; Muthusamy, Rajendiran; Srinivasan, Vimala; Chidambaram, Vivek; Karunakaran, Kiruthika

doi:10.11591/ijeecs.v32.i3.pp1503-1511

Cited by 2 publications

(2 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning models, in essence, reproduce how humans learn by making sense of instances. Deep learning techniques are characterized by their unique use of multi-layer neural networks and advanced supervised and unsupervised learning procedures [22], [23]. There is a noticeable degree of functional versatility with these models.…”

Section: Deep Learning (Cnn Classifier) Of 2d Model and 3d Modelmentioning

confidence: 99%

Revolutionization of augmented reality in tourism via deep learning

Essa,

Chaturvedi,

Khurana

2024

IJEECS

View full text Add to dashboard Cite

Tourism has become an integral part of social and economic development across the globe. It does not only serve as a recreational activity but also as a source of revenue for the nation. The paper systematically explores the potential enhancements in the tourist experience through cutting-edge technology. Employing deep learning methods, the study specifically concentrates on refining augmented reality encounters for visitors. The proposed approach utilizes deep learning algorithms to optimize and tailor tourists’ augmented reality experiences, addressing current sectoral challenges like customization and engagement shortcomings. The methodology’s selection is predicated on it is capability to elevate user experience, accurately identify objects, offer visual guided tours, integrate historical context, and ultimately propel augmented reality adoption in tourism. Notably, the investigation culminates in a noteworthy average accuracy of 99% when incorporating deep learning to enhance augmented reality in tourism.

show abstract

Section: Deep Learning (Cnn Classifier) Of 2d Model and 3d Modelmentioning

confidence: 99%

Revolutionization of augmented reality in tourism via deep learning

Essa,

Chaturvedi,

Khurana

2024

IJEECS

View full text Add to dashboard Cite

show abstract

“…Study demonstrates that Decision Tree and SVM algorithms outperform others, achieving superior accuracy and detection rates in identifying malicious network traffic. 2 Kannan,C et al [14] The study utilizes the Ryu controller and Mininet tool to address the impact of Denial of Service (DoS) attacks on Software-Defined Networking (SDN Experimental findings demonstrate that the ensemble approach in machine learning surpasses the performance of individual algorithms. demonstrating superior accuracy, detection rates, and lower false alarm rates.…”

Section: Accurately Detecting Malicious Trafficmentioning

confidence: 99%

Enhancing DDoS Attack Classification: Ensemble of ANN Models with SDN-Based Network Analysis

2024

IJRASET

View full text Add to dashboard Cite

In this survey optimization of Distributed Denial of Service (DDoS) attack classification has been explored. Dealing with the increasing frequency, and complexity of such attacks presents a substantial challenge to contemporary network infrastructures. An ensemble approach leveraging Artificial Neural Network (ANN) models is proposed to enhance accuracy and robustness. The integration of multiple neural network architectures, combined with the introduction of Software-Defined Networking (SDN), is emphasized as a crucial element for efficient network data analysis. SDN provides dynamic and programmable network management with real-time response capabilities. The fusion of ANN models and SDN-based analytics aims to improve DDoS attack detection precision while minimizing false positives. Thoroughly scrutinizing the strengths and weaknesses of diverse ANN architectures to assess their suitability for DDoS attack classification, the study has highlighted the impact of SDN on adaptability and responsiveness in network security. Positioning the ensemble approach as a comprehensive defense mechanism against the evolving DDoS threat landscape, the research illuminates not only the then-current state of DDoS attack classification, but also a proposed forward-looking methodology laying the groundwork for intelligent and adaptive security solutions aimed at safeguarding network infrastructures against persistent DDoS onslaughts

show abstract

Machine learning based detection of DDoS attacks in software defined network

Cited by 2 publications

References 31 publications

Revolutionization of augmented reality in tourism via deep learning

Revolutionization of augmented reality in tourism via deep learning

Enhancing DDoS Attack Classification: Ensemble of ANN Models with SDN-Based Network Analysis

Contact Info

Product

Resources

About