A confidence-based filtering method for DDoS attack defense in cloud environment

Distributed Denial-of-Service attack (DDoS) is a major threat for cloud environment. Traditional defending approaches cannot be easily applied in cloud security due to their relatively low efficiency, large storage, to name a few. In view of this challenge, a Confidence-Based Filtering method, named CBF, is investigated for cloud computing environment, in this paper. Concretely speaking, the method is deployed by two periods, i.e., non-attack period and attack period. More specially, legitimate packets are collected in the non-attack period, for extracting attribute pairs to generate a nominal profile. With the nominal profile, the CBF method is promoted by calculating the score of a particular packet in the attack period, to determine whether to discard it or not. At last, extensive simulations are conducted to evaluate the feasibility of the CBF method. The result shows that CBF has a high scoring speed, a small storage requirement, and an acceptable filtering accuracy. It specifically satisfies the real-time filtering requirements in cloud environment.