Gotham Dataset 2025 - Large-Scale IoT Network Intrusion Detection
Abstract
"Reproducible large-scale IoT network dataset from 78 emulated devices using MQTT, CoAP, and RTSP protocols. Includes benign and malicious traffic with DoS, brute force, scanning, and C&C attacks in PCAP and CSV formats."
Description
Dataset Overview
The Gotham Dataset 2025 is a large-scale, reproducible benchmark for evaluating decentralized Intrusion Detection Systems (IDS) and Federated Learning in virtualized smart cities.
Key Features
- 78 emulated IoT devices operating on MQTT, CoAP, and RTSP protocols
- Benign and malicious traffic captured in PCAP format using tcpdump
- Attack types: DoS, Telnet Brute Force, Network Scanning, CoAP Amplification, Mirai botnets, Merlin C2
- Distributed capture at each IoT gateway-device interface
- CSV format with extracted features using Tshark
- Preserves non-IID nature of edge data for realistic AI security training
Research Applications
- Intrusion Detection Systems for large-scale IoT
- Federated Learning benchmarking
- Decentralized security mechanisms
- Smart city network security
View Data Structure
To explore column names, data types, and sample rows, visit the official dataset page on Zenodo.
Preview on ZenodoCite This Dataset
Belarbi, Othmane, Mehta, Arzam, Poh, Gek Siong, Koh, Jun Yong, & De Mot, Ben (2025). Gotham Dataset 2025 - Large-Scale IoT Network Intrusion Detection. [Dataset]. Zenodo. https://doi.org/10.5281/zenodo.14618790
Source: Zenodo (2025) · DOI: 10.5281/zenodo.14618790
Indexed by IoTDataset.com on Mar 20, 2026
Ready to Start Your Research?
Download this dataset directly from the official repository and start building your next breakthrough project.