A Deep CNN Ensemble Framework for Efficient DDoS Attack Detection in Software Defined Networks

Abstract

As novel technologies continue to reshape the digital era, cyberattacks are also increasingly becoming more commonplace and sophisticated. Distributed denial of service (DDoS) attacks are, perhaps, the most prevalent and exponentially-growing attack, targeting the varied and emerging computational network infrastructures across the globe. This necessitates the design of an efficient and early detection of large-scale sophisticated DDoS attacks. Software defined networks (SDN) point to a promising solution, as a network paradigm which decouples the centralized control intelligence from the forwarding logic. In this work, a deep convolutional neural network (CNN) ensemble framework for efficient DDoS attack detection in SDNs is proposed. The proposed framework is evaluated on a current state-of-the-art Flow-based dataset under established benchmarks. Improved accuracy is demonstrated against existing related detection approaches. INDEX TERMS Software defined network (SDN), anomaly detection, distributed denial of service (DDoS), deep learning, deep convolutional neural network (CNN).

Applications and Evaluations ofBio-InspiredApproaches in Cloud Security: A Review

“…Haider et al [149] DDos Attack detection ID Deep CNN Improve accuracy and reduce time complexity Tang et al [150] Web attacks through encoder-decoder ID RNN signature-based WAFs with RNN Li et al [24] Keystroke analysis IA GA Identity based cloud computing Yu & Cho [25] Keystroke analysis IA GA-SVM Feature selection Nag et al [38] Adaptive selection IA GA Multi-factor authentication Gupta et al [151] Image processing IA GA Detect adversarial attacks Dasgupta et al [34] Adaptive selection IA GA Selection techniques for multi-factor authentication Raghavendra et al [17] Palm and face recognition IA SI Multi-sensor bio-metric analysis…”

A Weighted Ensemble Learning Algorithm Based on Diversity Using a Novel Particle Swarm Optimization Approach

“…Equation (4) indicates that under the premise of correct classification by one classifier, i.e., the ratio of the sum of the number of misclassified samples to the total number of samples in another classifier, this diversity measurement includes an accuracy factor. For the ensemble classifier with L classifiers, the diversity measure considering accuracy in the first stage of this paper can be calculated by Equation 5which represents the average of the sum of the diversity values of the paired classifiers.…”

“…Ensemble learning combines multiple individual learners to improve the generalization performance of an individual learner [1,2]. It is an important and popular branch of machine learning and is widely used in attack detection [3][4][5], fraud recognition [6,7], image recognition [8,9], biomedicine [10,11], intelligent manufacturing [12,13], time series analysis [14,15] and other fields. Ensemble learning usually involves multiple weak classifiers, such as decision trees [16], support vector machines [17], neural networks [18] and k-nearest neighbors [19], to form a strong classifier, multiple strong classifiers [20] or even a combination of multiple machine learners to complete the learning task.…”

Hybrid Deep Learning: An Efficient Reconnaissance and Surveillance Detection Mechanism in SDN

“…Thus, SDNs are flexible and innovative networks. A comprehensive and detailed overview of the SDN architecture can be found in author's published work [8], [13], [16]. Every SDN controller has ability to extend varied modules.…”

“…Further, the control plane-based orchestration for various underlying functions makes the SDN controller as the most potential part of the SDN architecture. On the contrary, the control plane is vulnerable and can be potentially targeted with varied evolving sophisticated lethal cyber threats and attacks such as denial of service (DoS), distributed denial of service (DDoS), Brute Force, web attacks and other application level attacks such as SQL injections, cross site scripting etc., that can simply lead to compromise the accessibility and confidentiality of data, processes of application or can even disrupt the entire network [5], [6], [7], [8]. The SDN networks beside leveraging huge benefits also present deviating security concerns and evolving threats.…”