Probabilistic Neural Network based attack traffic classification

Akilandeswari, V.; Shalinie, S. Mercy

doi:10.1109/icoac.2012.6416848

Cited by 23 publications

(8 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ANN is being used by several researchers to predict DDoS attacks, but using ANN model for real‐time data handling in cloud and fog is computational intensive and is not suitable if done training on static data. The behavior of training data is random, so training data set may be updated and must be done on real data.…”

Section: Related Workmentioning

confidence: 99%

Fog‐SDN: A light mitigation scheme for DDoS attack in fog computing framework

Priyadarshini

Barik

Dubey

2020

Int J Communication

View full text Add to dashboard Cite

Cloud computing is one of the most tempting technologies in today's computing scenario as it provides a cost-efficient solutions by reducing the large upfront cost for buying hardware infrastructures and computing power. Fog computing is an added support to cloud environment by leveraging with doing some of the less compute intensive task to be done at the edge devices, which reduces the response time for end user computing. But the vulnerabilities to these systems are still a big concern. Among several security needs, availability is one that makes the demanded services available to the targeted customers all the time. Availability is often challenged by external attacks like Denial of service (DoS) and distributed denial of service (DDoS). This paper demonstrates a novel source-based DDoS mitigating schemes that could be employed in both fog and cloud computing scenarios to eliminate these attacks. It deploys the DDoS defender module which works on a machine learning-based light detection method, present at the SDN controller. This scheme uses the network traffic data to analyze, predict, and filter incoming data, so that it can send the filtered legitimate packets to the server and blocking the rest. KEYWORDS fog computing, K nearest neighborhood, machine learning, Security, software-defined network, support vector machine Int J Commun Syst. 2020;33:e4389.wileyonlinelibrary.com/journal/dac

show abstract

Section: Related Workmentioning

confidence: 99%

Fog‐SDN: A light mitigation scheme for DDoS attack in fog computing framework

Priyadarshini

Barik

Dubey

2020

Int J Communication

View full text Add to dashboard Cite

show abstract

“…Niyaz et al [12] and Li et al [13] made use of the deep learning algorithm based on ANN to establish DDoS defense system with traffic trace. Probabilistic Neural Networks (PNN) is a supervised classifier of highprecision traffic identification [14], it is based on Bayesian minimum risk criterion. Self-Organizing Map (SOM) is an unsupervised competitive learning ANN [15].…”

Section: Related Workmentioning

confidence: 99%

“…In order to evaluate the performance of K-FKNN, we first make a comparison among K-FKNN and the same type algorithms, which include KNN [25], DPTCM-KNN [26], and KD tree [30]. Then, we conduct a comparison among K-FKNN and the algorithms of other types, which include PNN [14], SOM [18], SVM [21], and SVM-SOM [24]. The results are depicted in Fig.…”

Section: Performance Evaluation Of K-fknnmentioning

confidence: 99%

Efficient DDoS Detection Based on K-FKNN in Software Defined Networks

Sun

Feng³

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Software Defined Networking (SDN) centrally manages the network data layer to improve the programmability and flexibility of networks by the controller. Because of centralized control, SDN is vulnerable to Distributed Denial of Service (DDoS) attacks. In order to protect the security of SDN, a method based on K-means++ and Fast K-Nearest Neighbors (K-FKNN) is proposed for DDoS detection in SDN, and the modular detection system is presented in the controller. The detailed experiments are conducted to evaluate the system performance. The results of the experiments show that K-FKNN improves the detection accuracy and efficiency of K-Nearest Neighbors (KNN), and has high precision and stability of DDoS detection in SDN. INDEX TERMS Software defined networks, network security, DDoS detection, K-nearest neighbors.

show abstract

“…The datasets with qualitative variables was used for the experiment, since all the variable are not numerical in nature, it was normalized so that the neural network can learn it. [3] formulated model for Probabilistic Neural Network Based Attack Traffic Classification which detected a range of DDoS attacks and flash events. Their work centered on classifying Distributed Denial of Service attacks and Flash Events using Radial Basis Function Neural Network (RBFNN), Bayes inferences and Bayes decision rule as their tool for classification.…”

Section: Related Workmentioning

confidence: 99%

Distributed Denial of Service Detection using Multi Layered Feed Forward Artificial Neural Network

Idris¹,

Fabian²,

Abdulhamid³

et al. 2017

IJCNIS

View full text Add to dashboard Cite

Abstract-One of the dangers faced by various organizations and institutions operating in the cyberspace is Distributed Denial of Service (DDoS) attacks; it is carried out through the internet. It resultant consequences are that it slow down internet services, makes it unavailable, and sometime destroy the systems. Most of the services it affects are online applications and procedures, system and network performance, emails and other system resources. The aim of this work is to detect and classify DDoS attack traffics and normal traffics using multi layered feed forward (FFANN) technique as a tool to develop model. The input parameters used for training the model are: service count, duration, protocol bit, destination byte, and source byte, while the output parameters are DDoS attack traffic or normal traffic. KDD99 dataset was used for the experiment. After the experiment the following results were gotten, 100% precision, 100% specificity rate, 100% classified rate, 99.97% sensitivity. The detection rate is 99.98%, error rate is 0.0179%, and inconclusive rate is 0%. The results above showed that the accuracy rate of the model in detecting DDoS attack is high when compared with that of the related works which recorded detection accuracy as 98%, sensitivity 96%, specificity 100% and precision 100%.

show abstract

Probabilistic Neural Network based attack traffic classification

Cited by 23 publications

References 24 publications

Fog‐SDN: A light mitigation scheme for DDoS attack in fog computing framework

Fog‐SDN: A light mitigation scheme for DDoS attack in fog computing framework

Efficient DDoS Detection Based on K-FKNN in Software Defined Networks

Distributed Denial of Service Detection using Multi Layered Feed Forward Artificial Neural Network

Contact Info

Product

Resources

About