Network security engineers work to keep services available all the time by handling intruder attacks. IntrusionDetection System (IDS) is one of the obtainable mechanism that used to sense and classify any abnormal actions. Therefore, the IDS must be always up to date with the latest intruder attacks signatures to preserve confidentiality, integrity and availability of the services. The speed of the IDS is very important issue as well learning the new attacks. This research work illustrates how the Knowledge Discovery and Data Mining (or Knowledge Discovery in Databases) KDD dataset is very handy for testing and evaluating different Machine Learning Techniques. It mainly focuses on the KDD preprocess part in order to prepare a decent and fair experimental data set. The techniques J48, Random Forest, Random Tree, MLP, Naïve Bayes and Bayes Network classifiers have been chosen for this study. It has been proven that the Random forest classifier has achieved the highest accuracy rate for detecting and classifying all KDD dataset attacks, which are of type (DOS, R2L, U2R, and PROBE).
Cognitive radio technology enables unlicensed users (secondary users, SUs) to access the unused licensed spectrum which is allocated to primary users (PUs). In the literature, there are three traditional spectrum sharing paradigms that enable SUs to access the licensed spectrum. These access techniques include underlay, overlay and spectrum trading, and have their own drawbacks. To combat these drawbacks, we propose a new approach for each of them and merge them into one combined complete distributed system for cognitive network that contains all cognitive network functions. Our overlay scheme provides quick access to the unused spectrum because of the advantages of a distributed system where there is no contention for a central resource. We propose a new cooperative sensing protocol to enable the overlay scheme to reduce the likelihood of interfering with PUs and to avoid service interruption. We propose using our underlay scheme when the traffic loads at PUs are high that enables SUs to transmit simultaneously with PUs. The scheme uses reinforcement learning (RL) to manage the power of SUs and to protect PUs against harmful interference. Our trading scheme allows PUs to trade the unused spectrum for the SUs that require better quality of service. RL is used to control the size and the price for the rented spectrum. The new combined scheme increases the size of spectrum in the cognitive network because of using different access techniques based on their availabilities and requirements. Simulation results show the ability of the new scheme to serve extra traffic in the cognitive network.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.