ZMAD Devices' Pre-processed Traffic Dataset

This is the pre-processed dataset used in the paper:" ZMAD: Lightweight Model-based Anomaly Detection for the Structured Z-Wave Protocol".

The dataset can be used to test cybersecurity applications, Ai-based IDS, threat intelligence, and adversarial machine learning that target the Z-Wave protocol.

ZMAD dataset includes heterogeneous real Z-Wave devices traffic such as the main controller, several slaves' devices, actuators, and sensors.

The dataset consists of normal (benign) traffic and abnormal (attack) traffic collected from known Z-Wave vulnerabilities and fuzzing techniques.

Research paper details

C. K. Nkuba, S. Woo, H. Lee, and S. Dietrich, "ZMAD: Lightweight Model-based Anomaly Detection for the Structured Z-Wave Protocol," in IEEE Access, 2023.

Paper link: https://ieeexplore.ieee.org/document/10148964

For more information about the dataset, please contact Carlos Nkuba, on his email: carlosnkuba@korea.ac.kr.

Follow update at : https://github.com/CNK2100/ZMAD-Dataset

For the academic/public use, the researcher MUST cite the following papers:

C. K. Nkuba, S. Kim, S. Dietrich and H. Lee, "Riding the IoT Wave With VFuzz: Discovering Security Flaws in Smart Homes," in IEEE Access, vol. 10, pp. 1775-1789, 2022, doi: 10.1109/ACCESS.2021.3138768.
C. K. Nkuba, S. Woo, H. Lee, and S. Dietrich, "ZMAD: Lightweight Model-based Anomaly Detection for the Structured Z-Wave Protocol," in IEEE Access, 2023.

Last Updated: 08 June 2023