A collaborative intrusion detection system for Mobile Ad Hoc Networks using bayesian methods | |
| Author | Karim, Abul Hasanat Md. Rezaul |
| Call Number | AIT Thesis no.ICT-06-04 |
| Subject(s) | Mobile communication systems Computer security |
| Note | A thesis submitted in partial fulfillment of the requirements for the degree of Master of Engineering, School of Engineering and Technology |
| Publisher | Asian Institute of Technology |
| Series Statement | Thesis ; no. ICT-06-04 |
| Abstract | Mobile Ad-hoc network (MANET) is an emerging area of mobile computing. MANETs are becoming increasingly popular as more and more mobile devices find their way to the public, besides traditional uses such as battlefields and disaster situations. As the usage of MANETs is increasing day by day it demands security mechanism with higher efficiency and effectiveness. The concept and structure of MANETs make them prone to be easily attacked using several techniques often used against wired networks as well as new methods particular to MANETs. The wireless nature of communication and lack of any security infrastructure raise several security problems. Security issues arise in many different areas including physical security, key management, routing and intrusion detection, many of which are vital to a functional MANET. Intrusion preventive measures such as encryption and authentication can reduce intrusion but not eliminate them completely. Moreover, intrusion prevention is regarded as an after-thought during the design and development stages of computer systems. Hence there is the need for intrusion detection as it provides a second line of defense. This thesis work focuses on intrusion detection in MANET and proposes a new collaborative intrusion detection system using Bayesian method. A set of very useful features is used in order to ensure the effectiveness of the IDS. At the same time the Bayesian method improves efficiency in the detection procedure. The simulation result of around 95% over all accuracy demonstrates that this proposed intrusion detection system is effective against some known and unknown attacks those are related to the feature vectors. Considering the protocol independence of this method, it can be applied in any routing protocol with slight modifications. |
| Year | 2006 |
| Corresponding Series Added Entry | Asian Institute of Technology. Thesis ; no. ICT-06-04 |
| Type | Thesis |
| School | School of Engineering and Technology (SET) |
| Department | Other Field of Studies (No Department) |
| Academic Program/FoS | Information and Communication Technology (ICT) |
| Chairperson(s) | Rajatheva, R. M.A. Premanandana; |
| Examination Committee(s) | Ahmed, Kazi M.; Dailey, Matthew N. ; |
| Scholarship Donor(s) | Government of Finland;Asian Institute of Technology Fellowship; |
| Degree | Thesis (M.Eng.) - Asian Institute of Technology, 2006 |