kdaways.blogg.se

On a review of the literature, we can divide Skype classification methods into Is something important, particularly interactive traffic such as Skype. Therefore, Internet traffic classification To know the traffic carried in their networks for the purposes of optimising Internet Server Provider (ISP) and network operators are usually interested (2012), Baset and Schulzrinne (2006) and Zhang More explanations and details of how Skype elements communicateĬan be found by Adami et al. The first is responsibleįor authentication checking, the second make checks to update users’ versions Another two elementsĪre Skype Login Server (LS) and Skype Update Server. Networks among themselves, while SC tries to select an SN. Node with public address and adequate specification (CPU, RAM, etc.,). The second element is Super Node (SN) which is a Skype Client (SC) is a termįor the machine and software which runs the Skype application. Skype consists of several elements which are responsible for providing theĬonnection between the two communication parts. Skype is easy to use and provides a wide range of services such as voiceĪnd video calls, data transfer, video conference, instant message, online number, Also, atĬertain times, more than 22 million users were logged onto Skype at the same Skype users in the last year spent 1.8 billion h making video calls. One of the most popular forms of VoIP software. Over the last few years Skype has gained significant attention and has become

Information Technology Journal, 12: 1746-1754. A Skype Ml Datasets Validation and Detection Mechanism using Snort Rules and Statistical Approaches. Hamza Awad Hamza Ibrahim, Sulaiman Mohd Nor and Izzeldin Ibrahim Mohamed Abdelaziz, 2013. J48 was found to be the best resulting in more than 99% classification True Positive (TP). Four algorithms within Weka are used to examine the best algorithm for the given datasets.

Six Snort rules based on Skype login were proposed to generate training datasets as inputs to ML. Two different networks environment are considered for Skype traffic to gain insight into the statistical features of Skype traffic. This study highlights the problem of Machine Learning (ML) datasets validation and proposes a mechanism based on Snort rules and ML statistical approach to identify Skype traffic. However, the training and testing datasets validation have not been formally addressed. Several methods which used both signature-based and statistical approaches were proposed.

Skype traffic classification is challenging because Skype uses encrypted traffic and uses no well-known port number. Identification of real time applications such as Skype has gained more attention in the last few years. Internet traffic classification is an area of current research interest.