The Session Initiation Protocol (SIP) is one of the most common protocols that are used for signaling function in Voice over IP (VoIP) networks. The SIP protocol is very popular because of its flexibility, simplicity, and easy implementation, so it is a target of many attacks. In this paper, we propose a new system to detect the Denial of Service (DoS) attacks (i.e. malformed message and invite flooding) and Spam over Internet Telephony (SPIT) attack in the SIP based VoIP networks using a linear Support Vector Machine with l1 regularization (i.e. l1-SVM) classifier. In our approach, we project the SIP messages into a very high dimensional space using string based n-gram features. Hence, a linear classifier is trained on the top of these features. Our experimental results show that the proposed system detects malformed message, invite flooding, and SPIT attacks with a high accuracy. In addition, the proposed system outperformed other systems significantly in the detection speed.

Voice over Internet Protocol (VoIP) is a recent technology used to transfer media and voice over Internet Protocol (IP). Many organizations moved to VoIP services instead of the traditional telephone systems because of its low cost and variety of introduced services. The Session Initiation Protocol (SIP) is the most used protocol for signaling functions in VoIP networks. It has simple implantation but suffers from less protection against attacks. The Distributed Denial of Service (DDoS) attack is a dangerous attack that preventing legitimate users from using VoIP services and draining their resources. In this paper, we proposed an approach that utilizes deep learning to detect DDoS attacks. The proposed approach uses token embedding to improve the extracted features of SIP messages. Then, Convolutional Neural Network (CNN) was used to detect DDoS attacks with different intensities. Furthermore, a real VoIP dataset that contains different scenarios of attacks was used to evaluate the proposed approach. Our experiments find that the CNN model achieved a high F1 score (99-100%) as another deep learning approach that utilizes Recurrent Neural Network (RNN) but with less detection time. Also, it outperforms another system that depends on classical machine learning in case of low-rate DDoS attacks.

Further analysis and experimentation is carried out in this paper for a chaotic dynamic model, viz. the Nonlinear Dynamic State neuron (NDS). The analysis and experimentations are performed to further understand the underlying dynamics of the model and enhance it as well. Chaos provides many interesting properties that can be exploited to achieve computational tasks. Such properties are sensitivity to initial conditions, space filling, control and synchronization.Chaos might play an important role in information processing tasks in human brain as suggested by biologists. If artificial neural networks (ANNs) is equipped with chaos then it will enrich the dynamic behaviours of such networks. The NDS model has some limitations and can be overcome in different ways. In this paper different approaches are followed to push the boundaries of the NDS model in order to enhance it. One way is to study the effects of scaling the parameters of the chaotic equations of the NDS model and study the resulted dynamics. Another way is to study the method that is used in discretization of the original R\"{o}ssler that the NDS model is based on. These approaches have revealed some facts about the NDS attractor and suggest why such a model can be stabilized to large number of unstable periodic orbits (UPOs) which might correspond to memories in phase space.Comment: Computer Science & Information Technology, 2013, Vol. 4 No.