IFS — Intrusion forecasting system based on collaborative architecture

Abstract

Common methods for Intrusion Detection Systems (IDS) lack in security as they are postmortem approaches: Unwanted Internet Traffic (UIT) is detected and/or blocked only after UIT has inflicted serious damage. Even though some forecasting techniques have been applied to improve IDS in the last few years, three major gaps lie in those techniques: sensors employment, the use of just one forecasting technique and forecasts' sharing. The aim of this paper is to show a collaborative architecture of IDS with prediction approaches, covering the gaps of the current forecasting techniques. A proof of concept of such architecture is presented, which allows concluding about the improvement in forecasts for IDS to cope with UIT.