In the wake of growing concerns that Peer-to-Peer technology poses imminent threat upon the corporate networks, French-based software company Lynanda Computer Services has developed an advanced methodology to detect and block Skype traffic as a step in this direction.



As widely known, Skype’s VoIP protocol is proprietary and appears like a complete black box. Unlike other VoIP service providers, Skype utilizes a Peer-to-Peer Technology and other such obfuscation techniques. As a result, the network operators most of the times fail to identify Skype traffic. Lynanda states the application encrypts data send out over the Internet between peers and is particularly gifted when it comes to circumvent security limitations.



With a view to identify Skype’s traffic as it moves through the network, the research group at Lynanda has developed a new solution. It is purely based on statistical data-mining techniques, not on common firewall practices, as expected earlier.



The IT Solution provider claims that it is a two-step process to filter Skype.First; the firewall is exposed to its target environment to learn the particularities of Skype’s traffic. Then, it uses the information collected together with pattern-matching techniques to identify Skype’s related traffic.



The solution designed by Lynanda uses various technologies including neural networks, distributed statistical calculus, and pattern recognition through machine learning. These techniques are quite similar to the techniques implemented in financial statistics to find out regularities and typical patterns in apparently chaotic data like stock quotes.















Read