SPAD: A Session Pattern Anomaly Detector for Pre-alerting Intrusions in Home Network

Abstract

In order to prevent the intrusion in network-based information systems effectively, it is necessary to detect the early sign in advance of intrusion. This sort of pre-alerting approach may be classified as an active prevention, since detecting the various forms of hackers' intrusion trials to know the vulnerability of systems is not missed and early cross-checked. The existing network-based anomaly detection algorithms that cope with port-scanning and the network vulnerability scans have some weakness in slow scans and coordinated scans. Therefore, a new concept of pre-alerting algorithm is especially attractive to detect effectively the various forms of abnormal accesses for the trial of intrusion regardless of the intrusion methods. In this paper, we propose a session pattern anomaly detector (SPAD) which detects the abnormal service patterns by comparing them with the ordinary normal service patterns.