AN INTRUSION-TOLERANT INTRUSION DETECTION METHOD BASED ON REAL-TIME SEQUENCE ANALYSIS

摘要

One of the most advanced research issues in network security is intrusion-tolerant intrusion detection, which has become another essential technique to protect computer systems and prevent the intrusion from generating a system failure. This paper presents a novel intrusion-tolerant intrusion detection method based on real-time sequence forecast analysis for network stream. We devise linear regression techniques to forecast network stream sequences.According to these, it's helpful for us to analysis intruders'behaviors and to recognize undesirable intrusions. We also provide recovery strategies to tolerate intrusion. Experiments on the http server demonstrate that our method outperform the others.