Ad Hoc Network Intrusion Detection Number Of Key Technical Studies

Mobile Ad Hoc network (MANET) has become the focus in the research of wireless network. MANET with special nature is vulnerable to an adversary's malicious attacks. Moreover, the construction of the security system for MANET is more complicated. To study intrusion detection technology for mobile Ad Hoc network is a very significant work.With more and more application, security for mobile Ad Hoc networks becomes increasingly important. To secure mobile Ad Hoc networks, my dissertation will explore the security technologies in mobile Ad Hoc networks, including instruction detection model of Ad Hoc networks, algorithm of instruction detection. The contributions of this dissertation can be summarized as following:(1) A new detection method based on unsupervised learning is designed and implemented in this paper, which has the ability of discovering unknown kinds of attacks. It can be used not only as an independent analysis method, but also as an IDE (intrusion detection engine) in intrusion detection based on data fusion. In our method, Max-Min distance algorithm is employed as the core clustering algorithm, and some other techniques are also involved, such as nonlinear normalization pretreatment, efficiency coding of non-numerical feature etc. Its detection rate is distinctively higher than that of similar methods under the same experimental conditions, at the same false positive rate, especially for attacks from DOS and Probing.(2) A new mobile node intrusion location method is presented, according to the principle of positive selection. The behavior model whose frequency is higher will be analyzed and processed first. It improves the speed and effectiveness of intrusion detection. Intrusion Location is based on the event detection sequences correlation, graph theory and adjacency matrix are two methods to get the root failure sets. The experiment system implemented by this method shows a good diagnostic ability.