Recent Advances In Intrusion Detection. Improving Effectiveness Of Intrusion Detection By Feature Reduction Using LDA

      Аннотация: Threats to networks are numerous and potentially devastating. Intrusion detection is one of core technologies of computer security. Most of the existing IDs (Intrusion Detection systems) use all features in the network packet to look for known intrusive patterns, some of these features are irrelevant or redundant. A well-defined feature extraction algorithm makes the classification process more effective and efficient. This book approaches Linear Discriminant Analysis (LDA) with Back Propagation to address the problem of identifying important features in building an ID system, increase the convergence speed and decrease the training time. This book offers you a detailed and practical analysis with a fresh approach. An improved dataset (NSL-KDD) and effective classification is used to build the system that gives better and robust representation as it is able to transform features resulting in great data reduction, time reduction and error reduction in detecting new attacks. The content of the book is especially useful to professionals, students and researchers working in the field of Network Security & Privacy.

Ключевые слова: Feature extraction, Network Security, Intrusion Detection, Linear Discriminant Analysis, NSL-KDD