DELP-Net: A Differentiable Entropy Layer Pyramid Network for End-to-End Low-Rate DoS Detection
Open Access
Abstract
Low-rate Denial-of-Service (LDoS) attacks exploit periodic traffic pulses to trigger congestion while maintaining a low average rate, making them highly stealthy and difficult to distinguish from legitimate bursty traffic using threshold-based or simple statistical detectors. To address this challenge, this paper proposes DELP-Net, an end-to-end Differentiable Entropy Layer Pyramid Network for window-level online LDoS detection directly from raw traffic. DELP-Net combines a multi-scale one-dimensional convolutional pyramid with a differentiable Rényi-entropy-driven attention mechanism to capture distributional regularity and weak repetitive patterns characteristic of LDoS traffic. In addition, an entropy-conditioned temporal convolutional network is employed to model cross-window periodic dependencies in a lightweight manner, together with an entropy-regularized hybrid loss to enhance robustness under complex background traffic. Experiments on the low-rate DoS dataset show that DELP-Net achieves an average F1 score of 0.9877 across six LDoS attack types, with a detection rate of 98.69% and a false-positive rate of 1.15%, demonstrating its effectiveness and suitability for practical online intrusion detection deployments.Keywords
Funding Information
- National Natural Science Foundation of China (62302197)
- Jiaxing city science and technology project (2024AY40010)
This publication has 53 references indexed in Scilit:
- HawkEye: An end-host method to detect the Low-rate Denial-of-Service attack of cross-traffic over bottleneck linksComputer Networks, 2024
- Enhancing Network Threat Detection with Random Forest-Based NIDS and Permutation Feature ImportanceJournal of Network and Systems Management, 2024
- Deep intrusion net: an efficient framework for network intrusion detection using hybrid deep TCN and GRU with integral featuresWireless Networks, 2024
- DoS/DDoS attacks in Software Defined Networks: Current situation, challenges and future directionsComputer Communications, 2024
- Efficient Network Representation for GNN-Based Intrusion Detection2023
- CANET: A hierarchical CNN-Attention model for Network Intrusion DetectionComputer Communications, 2023
- A new DDoS attacks intrusion detection model based on deep learning for cybersecurityComputers & Security, 2022
- CBAM: Convolutional Block Attention Module2018
- Power spectrum entropy based detection and mitigation of low-rate DoS attacksComputer Networks, 2018
- Identifying LDoS attack traffic based on wavelet energy spectrum and combined neural networkInternational Journal of Communication Systems, 2017