Distributed Denial of Service Attack Detection in Application Layer Based on User Behavior

Distributed Denial of Service (DDoS) attacks are a threat to the security of red. In recent years,these attacks have been directed especially towards the application layer. This phenomenon ismainly due to the large number of existing tools for the generation of this type of attack. Thehighest detection rate achieved by a method in the application capacity is 98.5 percent.Therefore, the problem of detecting DDoS attacks persists. In this work an alternative ofdetection based on the dynamism of the web user is proposed. To do this, evaluate the user scharacteristics, mouse functions and right click. For the evaluation, a data set of 11055 requestswas used, from which the characteristics were extracted and entered into a classificationalgorithm. To that end, it can be applied once in Java for the classification of real users andDDoS attacks. The results showed that the evaluated characteristics achieved an efficiency of100 percent. Therefore, it is concluded that these characteristics show the dynamism of the userand can be used in a detection method of DDoS attacks.