The resources below include datasets and computational tools developed across different projects in which I have participated. They are available for use by the research, education, and professional communities, subject to the license and usage terms provided with each resource.
Dataset · Cyber threat intelligence
A collection of posts from Dark Web and Surface Web forums, with cybersecurity events classified by relevance. It supports research on threat intelligence, text mining, and machine-learning-based event detection.
Dataset · Malicious-content detection
A labeled collection of Brazilian Portuguese posts from Dark Web forums. It provides heuristic, manually reviewed, and model-generated labels for research on malicious-content detection and cyber threat intelligence.
Dataset · Cybercrime and judicial analytics
A dataset of public judicial decisions from the São Paulo Court of Justice related to cybercrime. It includes full text, metadata, topic-modeling labels, and a manually annotated subset for supervised classification.
Software ecosystem · Cybersecurity training
An open-source ecosystem that turns real security incidents into operational knowledge and practical learning content through anonymization, AI-assisted classification, playbook generation, human validation, and gamified activities.
Platform · IoT security and management
A platform for registering, connecting, monitoring, and protecting IoT devices in institutional networks. It integrates device management, security monitoring, and automated response through firewall policies.
Research framework · Intrusion detection
An experimental framework for studying how machine-learning intrusion-detection systems generalize across network-data domains. It includes flow extraction, dataset standardization, model training, inter-domain evaluation, and reproducibility resources.
Dataset and pipeline · DNS security
A curated dataset and experimental pipeline for detecting DNS-based data exfiltration over conventional DNS and DNS over HTTPS. It supports benchmarking, feature engineering, and machine-learning experiments.
Dataset · Sports analytics
A dataset with detailed statistics from Brazilian Série A football matches between 2018 and 2023, including dates, rounds, home and away teams, stadiums, results, and other match information.
Software tool · IoT fingerprinting
A prototype for identifying IoT devices through deterministic fingerprints derived from active probing and passive TCP/IP traffic analysis. It produces reproducible device identities that do not depend on IP addresses.
Research toolkit · Cyber threat intelligence
A collection of research tools for forum discovery and collection, relational storage, text normalization, malicious-content scoring, temporal topic analysis, and cross-domain evaluation of threat-intelligence models.
Software tool · IoT experimentation
A configurable simulator for IoT devices, sensors, batteries, network conditions, and atypical events. It supports large-scale CoAP simulations, MQTT gateways, scheduled scenarios, and live monitoring.