Comunicación presentada en: 17th International Conference on Computational Intelligence in Security for Information Systems (CISIS 2024) and 15th International Conference on European Transnational Education (ICEUTE 2024), 9-11 October 2024, Salamanca (Spain), The purpose of this research is to enhance the security of Internet of Things devices. The deployment of these gadgets has increased exponentially, nowadays they can be found in every sector from industrial environments to applications in residential homes. This technology is important for enterprises due to the ability to manage different kind of data and control critical operations in an efficiently way. Consequently, these devices have become frequent targets of cyberattacks, highlighting the necessity of robust detection methods. However it is a complicated task to find a uniform security solution due to the variety of devices, with different capabilities and requirements. This study evaluates some artificial intelligence supervised learning algorithms such as XGBoost and Random Forest using the TON_IoT dataset, which are new generations of Internet of Things and Industrial datasets for evaluating the fidelity and the efficiency of different cybersecurity applications based on Artificial Intelligence. The analysis shows both algorithms are effective in detecting cyberattacks, achieving accuracies close to 98%, with a minimal variation in terms of precision and recall. These algorithms outperform the results obtained in previous works with the same dataset, then they can provide an additional security layer, allowing accurate identification of potential attacks. This research shows the importance of artificial intelligence algorithms in cybersecurity and their potential to improve the protection of this kind of devices., This publication is part of the AI4SECIoT project (“Artificial Intelligence for Securing IoT Devices”), funded by the National Cybersecurity Institute (INCIBE) - Spanish Ministry of Economic Affairs and Digital Transformation, and the European Union (NextGenerationEU*/PRTR).

This dataset is a proportionally downsampled version of the NF-ToN-IoT V1 dataset [Sarhan et al., 2021; Sarhan et al., 2023]., This publication is part of the AI4SECIoT project (‘Artificial Intelligence for Securing IoT Devices’), funded by the National Cybersecurity Institute (INCIBE), derived from a collaboration agreement signed between the National Institute of Cybersecurity (INCIBE) and the University of Burgos. This initiative is carried out within the framework of the Recovery, Transformation and Resilience Plan funds, financed by the European Union (Next Generation), the project of the Government of Spain that outlines the roadmap for the modernization of the Spanish economy, the recovery of economic growth and job creation, for solid, inclusive and resilient economic reconstruction after the COVID19 crisis, and to respond to the challenges of the next decade.

These files consist of raw network packet captures (PCAP format) obtained from controlled laboratory experiments that emulate benign and malicious Internet of Things (IoT) traffic in fog computing environments. The experiments involved resource-constrained edge devices, specifically a Raspberry Pi 4 and a Jetson Nano. Malicious traffic corresponds to Denial-of-Service (DoS) attacks executed from the Jetson Nano against the Raspberry Pi 4 within an isolated local network, while benign traffic reflects typical IoT device behavior, including alert generation, DNS requests, and telemetry or device-management communications (e.g., MQTT updates).
All captures were performed under reproducible laboratory conditions and are intended to support research on intrusion detection, IoT network behavior analysis, and the development and training of cybersecurity attack detection models., This work was carried out under the project *AI4SECIoT – Artificial Intelligence for Securing IoT Devices*, funded by the Instituto Nacional de Ciberseguridad (INCIBE) within the framework of the *Plan de Recuperación, Transformación y Resiliencia*, financed by the European Union (Next Generation EU).

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., This research was supported by the project *AI4SECIoT – Artificial Intelligence for Securing IoT Devices*, funded by the Instituto Nacional de Ciberseguridad (INCIBE) within the framework of the *Plan de Recuperación, Transformación y Resiliencia*, financed by the European Union (Next Generation EU).

This dataset contains simulation data generated from two individual-based stochastic models for malware propagation in an Internet-of-Things (IoT) network: a continuous-time Gillespie SIR model and a discrete-time Monte Carlo SIR model.
For each modeling framework, two variants are included: the standard version (Gil / LMC) and the version incorporating the Topological Overlap Measure (TOM) (GilT / LMCTOM).
All simulations are executed on a 128-node IoT communication network generated as a power-law cluster graph.
Each simulation is stored as an independent CSV file in pivoted format, where rows represent network nodes and columns represent temporal steps produced by the algorithm (event steps in the Gillespie method and iteration steps in the Monte Carlo method).
The dataset is suitable for research on malware propagation, stochastic processes on networks, graph-based machine learning models, and cybersecurity analytics., This publication is part of the AI4SECIoT project ("Artificial Intelligence for Securing IoT Devices"), funded by the National Cybersecurity Institute (INCIBE), derived from a collaboration agreement signed between the National Institute of Cybersecurity (INCIBE) and the University of Burgos. This initiative is carried out within the framework of the Recovery, Transformation and Resilience Plan funds, financed by the European Union (Next Generation), the project of the Government of Spain that outlines the roadmap for the modernization of the Spanish economy, the recovery of economic growth and job creation, for solid, inclusive and resilient economic reconstruction after the COVID19 crisis, and to respond to the challenges of the next decade.