Software-Defined Networking (SDN) is a novel networking paradigm that provides enhanced programming abilities, which can be used to solve traditional security challenges on the basis of more efficient approaches. The most important element in the SDN paradigm is the controller, which is responsible for managing the flows of each correspondence forwarding element (switch or router). Flow statistics provided by the controller are considered to be useful information that can be used to develop a network-based intrusion detection system. Therefore, in this paper, we propose a 5-level hybrid classification system based on flow statistics in order to attain an improvement in the overall accuracy of the system. For the first level, we employ the k-Nearest Neighbor approach (kNN); for the second level, we use the Extreme Learning Machine (ELM); and for the remaining levels, we utilize the Hierarchical Extreme Learning Machine (H-ELM) approach. In comparison with conventional supervised machine learning algorithms based on the NSL-KDD benchmark dataset, the experimental study showed that our system achieves the highest level of accuracy (84.29%). Therefore, our approach presents an efficient approach for intrusion detection in SDNs.

Software-defined networking (SDN) represents a promising networking architecture that combines central management and network programmability. SDN separates the control plane from the data plane and moves the network management to a central point, called the controller that can be programmed and used as the brain of the network. Recently, the research community has shown an increased tendency to benefit from the recent advancements in the artificial intelligence (AI) field to provide learning abilities and better decision making in SDN. In this study, the authors provide a detailed overview of the recent efforts to include AI in SDN. The study showed that the research efforts focused on three main sub-fields of AI namely: machine learning, meta-heuristics and fuzzy inference systems. Accordingly, in this work, the authors investigate their different application areas and potential use, as well as the improvements achieved by including AI-based techniques in the SDN paradigm.

No abstract

Software-Defined Networking (SDN) is an emerging networking paradigm that provides an advanced programming capability and moves the control functionality to a centralized controller. This paper proposes a two-stage novel intelligent approach that takes advantage of the SDN approach to detect Denial of Service (DoS) flooding attacks based on calculation of packet rate as the first step and followed by Support Vector Machine (SVM) classification as the second step. Flow concept is an essential idea in OpenFlow protocol, which represents a common interface between an SDN switch and an SDN controller. Therefore, our system calculates the packet rate of each flow based on flow statistics obtained by SDN controller. Once the packet rate exceeds a predefined threshold, the system will activate the packet inspection unit, which, in turn, will use the (SVM) algorithm to classify the previously collected packets. The experimental results showed that our system was able to detect DoS flooding attacks with 96.25% accuracy and 0.26% false alarm rate.

I. IntroductionHuman action recognition has been one of the important research areas of both computer vision and machine learning for more than ten years. Because it has a lot of potential applications such as surveillance systems, human-computer interaction and sports video annotation [1][2][3][4][5]. Initially, human action recognition approaches take a number of frames from videos in order to extract a set of features such as 3D-SIFT [6], extended SURF [7] and HOG3D [8], Space Time Interest Points (STIPs) [9], and optical dense trajectories [10]. Recently, deep learning architectures are used in order to replace the feature engineering step with an automated process. In this paper, we use 3D Convolutional Neural Networks (CNNs) as a feature extractor method based on spatial and temporal dimensions. Extracted features were classified by support vector machines algorithm. Our proposed system is trained and evaluated on KTH dataset (Fig. 1) which consist of 6 action classes (boxing, hand-waving, handclapping, jogging, running and walking) performed by 25 actors and includes a total of 599 videos [11,12].