الفهرس 
IntroductionOnly 14 pages are availabe for public view
 |  | from | 160 |  |  |
| | | from | 160 | | |
Abstract
Network security is a major research area for both scientists and business. Intrusion Detection System (IDS) is one of the most challenging problems in Mobile Ad Hoc Networks (MANETs). The main reason resides behind the changing and uncertain nature of MANETs networks. Hence, a compensate evolving in the IDS would be converting the whole system to rely on uncertainty and indeterminacy concepts.
These concepts are the main issues in the fuzzy system and consequently in neutrosophic system. In neutrosophic system, each attack is determined by MEMEBERSHIP, INDTERMINACY and NONMEMEBERSHIP degrees. The main obstacle is that most data available are regular values which are not suitable for neutrosophic calculation.
Therefore, the preprocessing phase of the neutrosophic knowledge discovery system is essential. Converting the regular data to neutrosophic sets is a problem of generating the MEMEBERSHIP, NONMEMEBERSHIP and INDTERMINACY functions for each variable in the system. Self-Organized Feature Maps (SOFM) are unsupervised artificial neural networks that were used to build fuzzy MEMEBERSHIP function, hence they could be utilized to define the neutrosophic variable as well.
SOFMs capabilities to cluster inputs using self-adoption techniques have been utilized in generating neutrosophic functions for the subsets of the variables. The SOFM are used to define the MEMEBERSHIP, NONMEMEBERSHIP functions of the Knowledge Discovery/Data Mining (KDD) network attacks data available in the UCI machine learning repository for further processing in knowledge discovery.
Afterwards the preprocessing module generates the INDTERMINACY function from both of the MEMEBERSHIP, NONMEMEBERSHIP functions basing on the neutrosophic set definitions.
The thesis proposes a MANETs attack inference by a hybrid framework of SOFM and the Genetic Algorithms (GA). The hybrid utilizes the unsupervised learning capabilities of the SOFM to define the MANETs neutrosophic conditional variables.
The neutrosophic variables along with the training data set are fed into the Genetic Algorithms to find the most fit neutrosophic rule set. The neutrosophic correlation coefficient is selected as the fitness function to help in finding the rule set from a number of initial sub attacks where the propositions and consequences are highly correlated.
These neutrosophic classification rules are designed to detect unknown attacks in MANETs. The simulation and experimental results are conducted on the KDD-99 network attacks data available in the UCI machine-learning repository for further processing in knowledge discovery.
The proposed system proved its ability to detect attacks in MANETs environment with reasonable accuracy and lower false alarm rates in comparison with other IDS like C4.5, Support Vector Machine, Ant Colony Optimization and Particle Swarm Optimization. Hence, applying the neutrosophic concepts to the IDS enhances classification accuracy in MANETs significantly.