NOCTOWL: Adaptive Tree-Based Model for Network Anomaly Detection Under Delayed and Sampled Label Availability
Open Access
- 17 November 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 197899-197911
Abstract
The paper introduces NOCTOWL, an online, interpretable network intrusion detection system designed for streaming environments subject to distributional shifts, with delayed and partial label availability. The method combines the inherently explainable structure of a decision tree with a clustering-based strategy to create interpretable data partitions and incrementally adjust them in response to distribution shifts. The model further incorporates selective sampling to adapt to evolving distributions while preventing unnecessary growth. Experiments on five benchmark datasets simulating realistic operating conditions demonstrate that NOCTOWL achieves competitive performance compared to black-box state-of-the-art systems, while maintaining robustness under constrained annotation budgets.Keywords
Funding Information
- Project Panacea: A Model-Based Framework for Self-Protecting Systems through the Progetti di Ricerca di Rilevante Interesse Nazionale (PRIN) 2022 Program (2022Y45XE3)
This publication has 42 references indexed in Scilit:
- Deep learning-driven methods for network-based intrusion detection systems: A systematic reviewICT Express, 2025
- SFC-NIDS: a sustainable and explainable flow filtering based concept drift-driven security approach for network introspectionCluster Computing, 2024
- Network anomaly detection via similarity-aware ensemble learning with ADSimComputer Networks, 2024
- FlowTransformer: A transformer framework for flow-based network intrusion detection systemsExpert Systems with Applications, 2023
- Network intrusion detection based on n-gram frequency and time-aware transformerComputers & Security, 2023
- Robust unsupervised network intrusion detection with self-supervised masked context reconstructionComputers & Security, 2023
- An efficient network behavior anomaly detection using a hybrid DBN-LSTM networkComputers & Security, 2022
- A comparative evaluation of unsupervised deep architectures for intrusion detection in sequential data streamsExpert Systems with Applications, 2020
- Incremental Learning2015
- An incremental intrusion detection system using a new semi‐supervised stream classification methodInternational Journal of Communication Systems, 2015