摘要 : Denial-of-service (DoS) attacks comprised of large numbers of packet streams from different sources on the victim, consuming key resources and rendering it unavailable to authorized users. Hence, there is a need of new techniques ... 展开 Denial-of-service (DoS) attacks comprised of large numbers of packet streams from different sources on the victim, consuming key resources and rendering it unavailable to authorized users. Hence, there is a need of new techniques and tools to handle this kind of attacks before damaging wide areas. In modern electronic society, IDS have become a necessary component for protecting interconnection of computer resources very effectively. In this paper new hybrid based IDS model, based on Genetic Algorithm (GA) and Support Vector Machine (SVM) for DoS attacks Detection. Attacks are identified by training the SVM classifiers after extracting features from PMU 2014 datasets using Genetic Algorithm. SVM classifier deals with large volume of data, that it easy to detect suspicious behaviours, which takes short time for training and testing process. Genetic-SVM based on wrapper based feature selection which is superior than filter based feature selection. The proposed work was implemented in Mat lab7. 2. The result shows that the proposed hybrid IDS has high detection accuracy (99. 5%) and (0. 5%) of false alarms. 收起