Mobile Cloning

Only available on StudyMode
  • Topic: Neural network, Artificial neural network, Machine learning
  • Pages : 14 (4202 words )
  • Download(s) : 262
  • Published : October 3, 2012
Open Document
Text Preview
Mirela Sechi Moretti Annoni Notare1 Azzedine Boukerche2 Fernando A. S. Cruz1 Bernardo G. Riso1 Carlos B. Westphall1

1 Network and Management Laboratory Federal University of Santa Catarina (UFSC) {mirela, cruz, riso, westphal}

2 Department of Computer Sciences University of North Texas

Abstract: This work presents the development of a distributed security management system for telecommunication networks. The system consists in reducing the use of cloned mobile telephones using three main techniques: (1) An ISO Formal Technique (LOTOS) is used to specify and validate the system; (2) A Pattern Recognition Technique is used to classify the telephone users into classes in order to identify if a call does not correspond to the patterns of a specific user; and (3) Distributed Object Technique is used for the implementation of this distributed system (i.e., manager and agents). Keywords: Distributed Management, Telecommunication Security, Formal Description Technique, Pattern Recognition, CORBA.

The security management service is responsible for providing a safe environment for both the operation and management of resources in a domain [14, 15]. Safety and Security are two reliability properties of a system. A ‘safe’ system provides protection against errors of trusted users, while ‘secure’ system protects against errors introduced by untrusted users [1]. A comprehensive network security plan must encompass all the elements that make up the network and provide important services: Access (authorized users), Confidentiality, (information remains private), Authentication (sender is who he claims to be), Integrity (message has not been modified in transit) and Nonrepudiation (originator cannot deny that he sent the message) [4]. Our main objective is to augment the security in telecommunication networks, avoiding frauds of cloned mobile phones. In order to program a non genuine mobile cloned phone,for instance to debit calls from a genuine mobile phone, one only needs to buy a piece of portable radio equipment called a scanner, which registers the frequency in which mobile phones operate in its immediate surroundings. The person committing the fraud may, for example, park his car around a shopping center, jot down various frequencies, transfer the data to clones and then pass them on to whomever may be interested [7]. The present work makes use of formal description techniques to specify, validate (employing simulations, testing and verifications) and translate from specification code to implementation code. The specification is made in stepped refinements, using automatic tools to verify each refinement. LOTOS (Language of Temporal Ordering Specification) is the formal description technique (FTD) used by the Eucalyptus Toolbox employment. In addition, pattern recognition techniques are used to classify the telephone users into classes according to their usage logs. Such logs contain the relevant

characteristics for every call made by the user. From this classification it is easier to identify if a call does not correspond to the patterns of a specific user, and thus, identify whether the call was effected by a non-genuine caller. As a consequence, the immediate identification of a fraud (as opposed to the moment of receiving the monthly bill) will reduce losses for both users and carriers. We are convinced that the distributed systems which make use of this classified database can uncover frauds with greater ease than conventional systems, when a call is outside of the pattern of a particular user, that is, when a possible fraud occurs. Pattern Recognition techniques are used by the MatLab tool employment. With this software, neural network algorithms (such as k-means, p-nearest neighbour and gauss) are implemented. Moreover, due to the characteristics of the telecommunication networks – distributed and...
tracking img