The diploma thesis is focused on the detection of a slow DoS attack named SlowDrop. The attack tries to imitate a legitimate person with a slow internet connection and does not show a new strong signature, so the attack is difficult to detect. The diploma thesis is based on the work of Ing. Mazanek in which the SlowDrop attack script was created. At the theoretical level, the issue of DoS attacks is described in general, but also in particular. Furthermore, the work develops methods for solving the problem of SlowDrop attack detection. The methods are then defined in detail and tested in a simulation environment. The practical part describes data analysis, signature detection, anomaly detection using neural networks and a detection script. In all practical parts, the used technologies and solution procedures are described in detail. The specific implementation of the solution and the achieved results are also presented. Finally, the individual results are evaluated, compared individually, but also among themselves. The obtained results show that the attack is detectable using a neural network and by created detection script.