Five Philippine route groups provide curated ADS-B flight trajectory data for research on preprocessing, attacks, and detection. The dataset includes raw and processed CSV files, with each cleaned flight record containing timestamp, latitude, longitude, altitude, speed, and derived motion features. Alexander Bañados prepared this dataset for research on trajectory anomaly detection and adversarial attack generation, last updated on June 4, 2026.
Use Cases
- Studying flight-route preprocessing techniques based on raw and cleaned trajectory data.
- Developing machine-learning detection models for trajectory modification attacks based on the four file-level classes.
- Evaluating poisoning attacks and model robustness based on the included adversarially generated poison datasets.
- Conducting route-specific sequence classification based on data organized for five Philippine domestic routes.
Strengths
- Data is organized for five distinct Philippine domestic route groups: Cebu, Davao, Iloilo, Malay/Caticlan, and Puerto Princesa.
- Includes four file-level classes: authentic flights, modified-altitude attacks, modified-speed attacks, and modified-position attacks.
- Contains multiple data versions: raw route folders, cleaned per-flight datasets, model-ready sequence-window datasets, and generated poison datasets.
Limitations
- Column-level documentation is absent; field semantics must be inferred after download.
- Row count and total dataset size are unknown, which may limit suitability assessment.
- Data may reflect geographic bias inherent to the selected Philippine domestic routes.
Provenance
- Source
- Harvard Dataverse
- Collection Method
- Curated ADS-B flight trajectory data.
- Time Range
- null
- Freshness
- Last updated 2026-06 04 15:46:44; freshness should be verified.
- Geography
- Philippines (domestic routes: Cebu, Davao, Iloilo, Malay/Caticlan, Puerto Princesa)