Title
Exploiting encrypted and tunneled multimedia calls in high-speed big data environment.
Abstract
Due to the rapid increase in the speed as well as the number of users over the Internet, the rate of data generation is enormously grown. In addition, at the same rate, the multimedia transmission especially the usage of VoIP calls is rapidly growing due to its cost effectiveness, dramatic functionality over the traditional telephone network and its compatibility with public switched telephone network (PSTN). In most of the developing countries, internet service providers (ISPs) and telecommunication authorities are concerned in detecting such calls to either block or prioritize commercial VoIP. Signature-based, port-based, and pattern-based detection techniques are inaccurate due to the complex and confidential security and tunneling mechanisms used by VoIP. Therefore, in this paper, we proposed a generic, robust, efficient statistical analysis-based solution to identify encrypted and tunneled voice media flows. We extracted six statistical parameters, which are extracted for each flow and compared with threshold values while generating a number of rules to identify VoIP media calls. The paper also offers a complete architecture that can efficiently process high-speed traffic in order to detect VoIP flows at real-time. The proposed system, including the architecture and the algorithm, can be practically implemented in a real environment, such as ISP or telecommunication authority’s gateway. We implemented the system using the parallel environment of Hadoop ecosystem with Spark on the top of it to achieve the real-time processing. We evaluated the system by considering 1) the accuracy in terms of detection rate by computing the direct rate and false positive rate and 2) the efficiency in terms of processing power. The result shows that the system has 97.54% direct rate and .00015% false positive rate, which are quite high. The comparative study proved that the proposed system is more accurate than the existing techniques.
Year
DOI
Venue
2018
10.1007/s11042-017-4393-7
Multimedia Tools Appl.
Keywords
Field
DocType
VoIP, Big data, Tunneling, Hadoop, Spark
Telephone network,Spark (mathematics),Computer science,Public switched telephone network,Real-time computing,Encryption,Default gateway,Test data generation,Voice over IP,The Internet
Journal
Volume
Issue
ISSN
77
4
1573-7721
Citations 
PageRank 
References 
2
0.37
18
Authors
4
Name
Order
Citations
PageRank
muhammad mazhar ullah rathore130121.15
Awais Ahmad237945.85
Anand Paul352746.32
Seungmin Rho444138.53