Flow-Based IoT Datasets for Cyberattack Detection and Generalization Studies (NFStream and Tranalyzer Tools) [Dataset]  

Abstract

This repository provides flow-based IoT traffic datasets generated through NFStream and Tranalyzer for cyberattack detection and generalization studies. The datasets originate from two data sources: (1) **UBU-LAB**, representing traffic captured in controlled IoT laboratory conditions, and (2) **ToN-IoT**, a public dataset containing benign and Denial-of-Service (DoS) traffic traces (available at https://research.unsw.edu.au/projects/toniot-datasets).

All datasets have been processed and structured to support experiments on flow extraction tool comparison and cross-domain generalization using Multilayer Perceptron (MLP) models. The repository contains: - Raw extracted flows for both NFStream and Tranalyzer, - Balanced datasets used in comparative studies (Paper 2), and - Datasets generated for generalization strategies (Paper 3).

The data files are ready to be reused or integrated into new modelling pipelines for IoT network security research.