Branly Martínez
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Branly Martínez has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Daniel Urda
Universidad de Burgos
5 shared publications - Jaime Andres Rincon
Universidad de Burgos
4 shared publications - Carlos Cambra
Universidad de Burgos
3 shared publications - Alejandro Diez Bermejo2 shared publications
- Antonio Díaz-Longueira
University of A Coruña, CTC, CITIC
1 shared publication - Beatriz Gil-Arroyo
Universidad de Burgos (Spain)
1 shared publication
Latest Publications
- Open Access
- 27 July 2026
- Published by Elsevier in Internet of Things
- Vol. 39
Cross-domain generalization strategies for IoT cyberattack detection using flow-based features
- 27 July 2026
- Published by Elsevier in Internet of Things
- Vol. 39
Open AccessCross-domain generalization strategies for IoT cyberattack detection using flow-based features
- 17 June 2026
- Published by Springer Nature
- p. 212-223
Machine Learning Validation of a Flow-Based IoT Cyberattack Dataset
- 17 June 2026
- Published by Springer Nature
- p. 212-223
Machine Learning Validation of a Flow-Based IoT Cyberattack Dataset
- Open Access
- 7 April 2026
- Published by Elsevier in SSRN Electronic Journal
iottrafficgen: A Reproducible Framework for IoT Traffic Generation in Cybersecurity Research
Experimental IoT cybersecurity studies often rely on ad hoc traffic-generation workflows that are difficult to reproduce, inspect, and audit across laboratories. iottrafficgen is an open-source Python framework that addresses this problem through declarative YAML scenarios, reusable tool profiles, structured execution metadata, and optional UDP ground-truth markers. The current release (v0.1.0) includes 66 predefined scenarios and 64 reusable profiles spanning seven attack categories plus benign IoT baseline generation. Each execution produces timestamped logs and JSON metadata recording resolved parameters, timing, return codes, and output artifact paths. When enabled, the marker subsystem emits start and end events that can be captured together with packet traces to support precise temporal alignment. By converting traffic-generation campaigns into versioned, machine-readable artifacts, iottrafficgen improves repeatability, traceability, and extensibility for controlled IoT cybersecurity experimentation and dataset construction.
- 7 April 2026
- Published by Elsevier in SSRN Electronic Journal
Open Accessiottrafficgen: A Reproducible Framework for IoT Traffic Generation in Cybersecurity Research
Experimental IoT cybersecurity studies often rely on ad hoc traffic-generation workflows that are difficult to reproduce, inspect, and audit across laboratories. iottrafficgen is an open-source Python framework that addresses this problem through declarative YAML scenarios, reusable tool profiles, structured execution metadata, and optional UDP ground-truth markers. The current release (v0.1.0) includes 66 predefined scenarios and 64 reusable profiles spanning seven attack categories plus benign IoT baseline generation. Each execution produces timestamped logs and JSON metadata recording resolved parameters, timing, return codes, and output artifact paths. When enabled, the marker subsystem emits start and end events that can be captured together with packet traces to support precise temporal alignment. By converting traffic-generation campaigns into versioned, machine-readable artifacts, iottrafficgen improves repeatability, traceability, and extensibility for controlled IoT cybersecurity experimentation and dataset construction.
- Open Access
- 24 March 2026
- Published by Elsevier in Data in Brief
- Vol. 66, 112717
Labelled IoT flow-based network traffic dataset for cyberattack detection
- 24 March 2026
- Published by Elsevier in Data in Brief
- Vol. 66, 112717
Open AccessLabelled IoT flow-based network traffic dataset for cyberattack detection
- 1 October 2025
- Published by Springer Nature
- p. 289-300
Optimal Malware Mitigation in IoT Networks: A Comparative Study of Neural ODEs and Pontryagin’s Maximum Principle
- 1 October 2025
- Published by Springer Nature
- p. 289-300
Optimal Malware Mitigation in IoT Networks: A Comparative Study of Neural ODEs and Pontryagin’s Maximum Principle