Gotham Dataset 2025: Large-Scale Federated IoT IDS Benchmark
Catalog Summary
"The Gotham Dataset is a large-scale, reproducible benchmark for evaluating decentralized Intrusion Detection Systems (IDS) and Federated Learning in virtualized smart cities. It captures interface-level network traffic from 78 heterogeneous IoT devices, including complex attack vectors like Mirai botnets, Merlin C2 traffic, and CoAP amplification, preserving the non-IID nature of edge data for realistic AI security training."
Catalog Notes
Overview
The Gotham Dataset 2025 is designed to move beyond centralized security models by providing granular, device-level traffic captures from a virtualized urban IoT infrastructure. It is specifically structured to support Federated Learning (FL) research where data remains local to each node.
What’s inside
- Data modalities: Structured CSV files containing extracted network features from packet captures.
- Scale: 78 unique IoT devices including sensors, actuators, and controllers.
- Metadata: Device IDs, interface identifiers, and detailed attack timestamps.
Collection / Setup
- Generated using the open-source Gotham testbed for high reproducibility.
- Captures traffic at the individual node interface level to maintain data skew (non-IID).
Labels / Targets
- Attack types: Mirai Botnet, Merlin C2 (HTTP/1-3/QUIC), Masscan, Nmap, CoAP reflection, and various UDP/TCP Floods.
Recommended tasks
- Federated Learning benchmarking
- Anonymized intrusion detection
- Distributed anomaly detection
- Privacy-preserving AI validation
Limitations
- Data is synthetic/simulated via a testbed rather than physical urban sensors.
- Requires concatenation for centralized learning tasks.
Access & License
View Data Structure
To explore column names, data types, and sample rows, visit the official dataset page on Kaggle.
Preview on KaggleCite This Dataset
Belarbi, O., Spyridopoulos, T., Anthi, E., Rana, O., Carnelli, P., & Khan, A. (2025). Gotham Dataset 2025: A Reproducible Large-Scale IoT Network Dataset for Intrusion Detection and Security Research. [Dataset]. Zenodo. https://doi.org/10.5281/zenodo.14502760
Source metadata: Zenodo (2025) · DOI: 10.5281/zenodo.14502760
Indexed by IoTDataset.com on Feb 05, 2026
Review the Source Record
Confirm the licence, version, access conditions, file format, and provenance at the source before use.