Detection of Denial of Service Attacks Using Echo State Networks

Abstract

Denial of Service (DoS) and Distributed Denial of Service (DDoS) attacks are major threats to cybersecurity in communication networks. These cyber attacks are evolving and becoming more difficult to identify and, hence, a number of intrusion detection approaches have been proposed. Various machine learning techniques have proved useful in detecting such anomalies. We rely on supervised machine learning and apply echo state networks to detect known DoS and DDoS attacks. Echo state networks belong to a reservoir computing approach used to train recurrent neural networks. Their performance is compared to bidirectional long short-term memory using datasets collected by the Canadian Institute for Cybersecurity and the RIPE and Route Views data collection sites. Performance is evaluated based on accuracy, F-Score, false alarm rate, and training time. Experimental results indicate that echo state networks have comparable performance and shorter training time.

Related publications

• Virtual Network Embedding for Switch-Centric Data Center NetworksIEEE International Symposium on Circuits and Systems proceedings · 2021 · Citations: 4 · Same author: Kamila Bekshentayeva
• Detection of Denial of Service Attacks in Communication NetworksIEEE International Symposium on Circuits and Systems proceedings · 2020 · Citations: 38 · Same author: Kamila Bekshentayeva
• An Investigation of an Explainability-Driven Hybrid Model for Flow-Based Intrusion DetectionIEEE International Conference on Smart Information Systems and Technologies · 2026 · Shared topic: Network Security and Intrusion Detection
• Anomaly detection in encrypted network traffic using self-supervised learningScientific Reports · 2025 · Citations: 34 · Shared topic: Network Security and Intrusion Detection