A Distributed Denial of Service (DDoS) attack occurs when an intruder or a group of attackers attempts to prevent legitimate users from accessing a service. A DoS attack is carried out by a single system, while a DDoS attack is carried out by several systems. DDoS attacks can be directed at various OSI layers. Deep learning has played a significant role in the growth of intrusion detection solutions in recent years. The primary goal of this work is to detect and identify DDoS attacks in the OSI model's application, network, and transport layers using deep learning models. The proposed models have been tested against the CICDDoS2019 dataset. The CICDDoS2019 data set contains network and transport layer DDoS attacks. For the CICIDDOS2019 dataset, DNN, LSTM, and GRU achieved an average accuracy of 99.32%, 99.4%, and 92.5%, respectively. The proposed models' performance is compared to that of a few other higher-accuracy models and found that the proposed models have higher accuracy with fewer epochs.
Performance Evaluation of Deep Learning Models in Detection of Distributed Denial of Service Attacks
02.12.2021
771803 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Detection of Distributed Denial of Service Attacks Based on Flow Connection Density
British Library Online Contents | 2004
|Automatic Detection of Distributed Denial of Service Attacks Based on Time-Frequency Analysis
British Library Online Contents | 2004
|Automatic Detection and Mitigation of Denial-of-Service Attacks
Europäisches Patentamt | 2022
|Assessing and quantifying denial of service attacks
Tema Archiv | 2001
|