Uma técnica de detecção de ataques DDoS baseado na Teoria do Caos utilizando a Densidade de Máximos

Abstract

Distributed Denial of Service (DDoS) attacks are one of the major problems affecting Internet stability, an early detection of the attack is still an important factor for mitigation measures. In this work, we present an algorithm that analyzes and detects DDoS attacks in the network data flow. It uses the Density of Maxima technique based on the Chaos Theory. The experiments were performed using synthetic traffic data generated with the JMeter tool, actual data from the 1998 World Cup, data sets from CAIDA 2007 and DARPA 2009. All experiments demonstrated the effectiveness of the technique in identifying the time of the attacks, as well as the suitability of our proposal to be used together with a DDoS detection algorithm.