Research Direction Towards Distributed Denial of Service Atttack Detection Algorithms for Enhancing Network Security

• Published in: 2023 4th International Conference on Smart Electronics and Communication (ICOSEC) pp. 713 - 721
• Main Authors: Dora, V Raghava Swamy, Lakshmi, V Naga
• Format: Conference Proceeding
• Language: English
• Published: IEEE 20.09.2023
• Subjects: Attack Detection; Deep learning; Deep Learning Algorithms; Denial-of-service attack; Distributed Denial of Service; Machine learning algorithms; Measurement; Network security; Performance Analysis; Surveys; Telecommunication traffic
• DOI: 10.1109/ICOSEC58147.2023.10275932

Due to the emerging of service providers over the internet, it causes more cyber attacks. The most common attack is Distributed Denial of Service (DDoS) attacks, which hardly interrupt the services. The major factor in fighting against DDoS attacks is the early separation and detection of network traffic. These attacks are threats over the internet, which drain more victims' resources and reduce the network bandwidth. In recent years, different defense strategies are offered against DDoS attacks, such as attack traceback, characterization, reaction, prevention, and detection. Thus, the attack of DDoS is increased in every year, which affects the network security. Various techniques were developed to detect the DDoS attack in the network. However, recent works have been adopted to show different anomaly-based and signature-based methods for detecting DDoS attacks. Thus, it is focused only on the nature of anomalies. Some of the detection methods do not offer proficient real-time detection with low faux pas and high detection rates. The main intention of this survey work is focused to categorize various algorithms for detecting DDoS attack to gain deep insight into the DDoS problem for beginners in this research area so that the features and challenges of each algorithm will get to know for enhancing the detection performance in the future through developing new innovative techniques. Moreover, various machine learning and deep learning techniques are reviewed in this work to detect DDoS attack. Additionally, this review explores various implementation platforms investigated for DDoS attack detection. However, this review explores various datasets, standard tools, and diverse performance metrics for experimentation. Consequently, this review focused on the research gaps and challenges are stated to focus future researchers for the DDoS detection model. Thus, this review helps the researchers to develop a new innovative model to prevent DDoS attacks for enhancing network security.