Toward lightweight detection and visualization for denial of service attacks

摘要: In this paper, we present a lightweight detection and visualization methodology for Denial of Service (DoS) attacks. First, propose new approach based on Random Forest (RF) to detect DoS The classify-cation accuracy RF is comparable that Support Vector Machines (SVM). also able produce the importance value individual feature. We adopt select intrinsic important features detecting attacks in way. And then, with selected features, plot both normal traffics 2 dimensional space using Multi-Dimensional Scaling (MDS). results show simple MDS can help one visualize without any expert domain knowledge. experimental KDD 1999 intrusion dataset validate possibility our approach.