A Selective Defense for Application Layer DDoS Attacks

Abstract

Distributed Denial of Service (DDoS) attacks remain among the most dangerous and noticeable attacks on the Internet. Differently from previous attacks, many recent DDoS attacks have not been carried out over the network layer, but over the application layer. The main difference is that in the latter, an attacker can target a particular application of the server, while leaving the remaining applications still available, thus generating less traffic and being harder to detect. Such attacks are possible by exploiting application layer protocols used by the target application. This paper proposes a novel defense for Application Layer DDoS attacks (ADDoS) based on the Adaptive Selective Verification (ASV) defense used for mitigating Network Layer DDoS attacks. We formalize our defense mechanism in the computational system Maude and demonstrate by using the statistical model checker PVeStA that it can be used to prevent ADDoS. In particular, we show that even in the presence of a great number of attackers, an application running our defense still has high levels of availability. Moreover, we compare our results to a defense based on traffic monitoring proposed in the literature and show that our defense is more robust and also leads to less traffic.