Skip to content

Time Matters: Temporal NetFlow Features for ML-Based Network Intrusion Detection

Mar 2025 · IEEE Access · Vol 14, pp. 66899-66913 · 21 citations · 81 references
Computer Science

TL;DR

The results demonstrate that augmenting conventional flow features with temporal information yields consistent gains; binary detection improves by up to 3% in F1 score, while macro-averaged multi-class F1 increases by approximately 27%, with the most significant improvements occurring in attack classes with pronounced temporal signatures.

Abstract

Most machine learning-based network intrusion detection systems (NIDS) rely on per-flow time-agnostic feature vectors, representing each flow using structural NetFlow features without explicit temporal information. This representation limits the ability to capture the intrinsic temporal structure of network traffic, such as event sequencing, inter-arrival dynamics, and non-stationary rate fluctuations. Consequently, the contribution of these temporal dependencies to detection performance remains under-characterised. In this work, we evaluate the extent to which sequential architectures, specifically Transformers, Long Short-Term Memory networks, and one-dimensional Convolutional Neural Networks, can exploit time-dependent information under controlled cross-dataset conditions. To facilitate this analysis, we introduce NF3, a temporally enriched extension of existing NetFlow-based benchmarks, which integrates fine-grained timestamps and inter-arrival-time statistics. Using these augmented datasets, we quantify temporal regularities in benign and malicious traffic and benchmark the ability of each architecture to learn time-dependent representations in both binary and multi-class settings. Our results demonstrate that augmenting conventional flow features with temporal information yields consistent gains; binary detection improves by up to 3% in F1 score, while macro-averaged multi-class F1 increases by approximately 27%, with the most significant improvements occurring in attack classes with pronounced temporal signatures. These findings indicate that incorporating time-dependent information enhances both the discriminative power and behavioural interpretability of modern NIDS.

Read PDF

Similar papers

Open access Aug 2026

Performance and Structural Symmetry Evaluation of Machine Learning-Driven Intrusion Detection Systems in Software-Defined Networks

This paper evaluates an ultra-compact five-feature polling scheme (F1–F5) designed to preserve statistical symmetry between control-plane monitoring and telemetry overhead within a dynamic Mininet–Ryu testbed and reveals that tree-based ensembles consistently outperform deep learning approaches.

Rohan Giri, Abdussalam Salama, Reza Saatchi et al. · 0 citations
#graph neural networks Open access Sep 2026

Online intrusion detection in computer networks using edge-aware attentive graph neural network

This study presents an intrusion detection framework based on a GNN that represents packet-flow data as communication graphs constructed over temporally segmented time windows, using a time-window-driven graph construction method that effectively models the temporal evolution of communication patterns while maintaining...

Áron Kiss, K. Nehéz, O. Hornyák · 0 citations
Open access Aug 2026

An enhanced multi-model ensemble learning architecture for robust network intrusion detection

An Enhanced Multi-Model Ensemble Network Intrusion Detection System (EME-NIDS), a deep meta-learning system that combines five different heterogeneous learning paradigms, including Convolutional Neural Networks, Dense Neural Networks, Transformers, XGBoost, and Random Forests is introduced.

Dwarsala Sireesha, Kakelli Anil Kumar · 0 citations
Open access 2026

A Time–Frequency Multi-Task Framework for Network Monitoring and Anomaly Detection

The Time-Frequency Multi-Task Network (TFMTNet), a self-supervised framework that provides a transferable representation module for the evaluated network telemetry tasks, and learns representations that can feed downstream reasoning and control modules, thereby supporting the perception, reasoning, and control loop in...

Qi Qi, Chengsen Wang, Xingyue Wang et al. · 0 citations
#machine learning Preprint Sep 2026

Statistical Feature Augmentation for Anomaly Detection in Dynamic Graphs

A statistical feature augmentation method that explicitly encodes behavioral interaction statistics into the input feature space and consistently improves detection performance is proposed, showcasing a promising approach for merging classical network analysis with deep learning.

Philipp Schlinge, Jean-Luc Schnipper, M. Atzmueller · 0 citations
Open access Aug 2026

A hybrid eBPF/ML intrusion detection system with two-model heterogeneous ensemble learning and real-time gateway-mode network blocking

A hybrid architecture that pushes 23-dimensional flow-feature extraction into the Linux kernel using an eXpress Data Path (XDP) eBPF program, and combines it with a heterogeneous, calibrated two-model ensemble in user space is presented.

Y. Alnattaf, Hanaa F. Mahmood · 0 citations

Related blog posts

Microsoft Research Blog Nov 3, 2026

Learn the rules: The hacker mindset

Research Manager Mike Walker reflects on a career spanning hacker culture, cybersecurity, and AI, sharing lessons about trust, teamwork, leadership, and why solving difficult problems requires curiosity, judgment, agility—and an understanding of the rules. The post Learn the rules: The hacker mindset appeared first on Microsoft Research.

MIT News · Artificial Intelligence Nov 17, 2026

Learning the language of machine learning

By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.

Microsoft Research Blog Nov 16, 2026

TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient

AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.