UNSW-IoTraffic: Consumer IoT Packets, Flows and Protocols
Consumer IoT network traffic from 27 devices over about 203 days: 95.5 million packets and 4.9 million flows, released as packet, flow and protocol files.
View DatasetShowing 12 of 51 datasets
Consumer IoT network traffic from 27 devices over about 203 days: 95.5 million packets and 4.9 million flows, released as packet, flow and protocol files.
View DatasetNine attack captures for network intrusion detection, with a documented total of 27,170,754 packets, 115 statistical features per packet and separate binary labels.
View DatasetPublisher-reported 49,902,287 labeled IoT/IIoT records with 88 columns; the inspected attack log contains 302 sessions across 14 attack types.
View DatasetSmart home traffic captured under normal operation and seven multi-stage attack scenarios across heterogeneous end devices. CC BY 4.0, published 2026.
View DatasetInternet of Medical Things IDS dataset with BLE, IP packet, and IP flow captures. CSV and pickle formats, 2.7 GB, for ML-based healthcare IoT intrusion detection.
View DatasetFree CC0 synthetic dataset: 4,000 rows of Modbus, OPC UA and DNP3 flows labelled for SCADA intrusion detection. 21% Attacks. Reproducible from its seed.
View DatasetReal IoT botnet traffic dataset from 9 commercial devices (webcams, routers, thermostats) authentically infected by Mirai and BASHLITE. Over 7M records, 115 statistical features. CSV format. Benchmark for deep-learning-based IoT anomaly and botnet detection.
View DatasetLarge-scale distributed IoT IDS benchmark with traffic captured at individual device interfaces across 78 heterogeneous smart city IoT devices using the Gotham testbed. PCAP and CSV. Published January 2026 on Zenodo. Designed for federated learning and decentralised IDS research.
View DatasetFirst open Zigbee IoT dataset with fully decrypted payloads, captured from a real smart home with 15 Zigbee devices over 20 days. Distributed as a single archive (dataset.tar.gz, 663.4 MB) of pcap captures with the network key included. Published October 2024 on Zenodo under CC BY 4.0.
View DatasetFree CC0 synthetic dataset: 10,000 rows of Modbus, OPC UA and DNP3 flows labelled for SCADA intrusion detection. 29% Attacks. Reproducible from its seed.
View DatasetLarge-scale IoT cybersecurity dataset with 47M+ labeled network flows from 105 real IoT devices across 33 attack types in 7 categories. PCAP and CSV formats. Built for IDS/IPS development and ML-based IoT traffic classification research.
View DatasetHeterogeneous IoT/IIoT dataset from UNSW Canberra Cyber Range with network traffic, Windows/Linux OS traces, and IoT sensor telemetry. Labeled for 9 attack types including DoS, DDoS, ransomware, and XSS. CSV and PCAP formats. Benchmark for AI-based IDS evaluation.
View Dataset