Cyber Weather Forecasting: Forecasting Unknown Internet Worms Using Randomness Analysis

摘要: Since early responses are crucial to reduce the damage from unknown Internet attacks, our first consideration while developing a defense mechanism can be on time efficiency and observing (and predicting) change of network statuses, even at sacrifice accuracy. In recent security field, it is an earnest desire that new predict future attacks needs developed. This motivates us study forecasting toward atacks, which referred as CWF (Cyber Weather Forecasting). this paper, in order show principle realized real-world, we propose called FORE (FOrecasting using REgression analysis) through real-time analysis randomness traffic. responds against worms 1.8 times faster than detection mechanism, named ADUR (Anomaly Detection Using Randomness check), detect worm when only one percent total number vulnerable hosts infected. Furthermore, give timely information about process current situation. Evaluation results demonstrate prediction proposed including ability behaviors starting 0.03 infection. To best knowledge, achieve attacks.