DEPARTMENT OF COMPUTER SCIENCE
Manipur University
MU-IoT Dataset
The MU-IoT dataset is an IoT intrusion dataset generated in the IoT Smart Lab at Manipur University, Canchipur, Imphal-795003, Manipur, India. The dataset contains 22.8 GB raw network traffic collected from our own network testbed environment. The dataset can be used to develop IoT intrusion detection and also to validate intrusion prevention systems. The captured network traffic is pre-processed to extract and select network traffic flow features for converting the whole dataset to a standard one. The standard dataset size is 15.8 GB that contain Sixteen different types of attack scenarios. The attacks are generated both in the application layer and the Network layer of our IoT testbed network. The preprocessed network data contains 121 flow-based features and 3 class labels of more than 34.8 million records. Additionally, this dataset covers extensive IoT-specific application protocols and a variety of normal network behaviours, which is a notable advantage over existing datasets. The MU-IoT dataset can be utilized to develop and validate machine learning-based Intrusion Detection and Mitigation Systems (IDMS). Moreover, the MU-IoT dataset helps to validate the centralized and federated learning-based IDMS. A detailed description of the network testbed is shown in the following figure.
Testbed Diagram
How to use the dataset?
The dataset can be used in two form, viz., raw form and preprocessed form. In case of raw form researcher need to perform network traffic engineering for feature extraction and feature selection. Moreover, the dataset is fully labelled and hence researchers can develop intrusion detection system using Machine Learning or Deep Learning methods. In case of preprocessed form, researchers can directly use the dataset to develop IDS and IPS. In addition, the dataset would help in validating the effectiveness of the IDSs considering all the 16 different types of attacks.
Repository Structure
The repository consists of the following directories:
- PCAP: Contains the original raw network traffic in '.pcap' format.
- CSV: Contains the extracted network traffic data in '.csv' format.
- FinalDataset: Contains the final dataset 'MU-IoT.csv' for analysis.
- MISC: Contains supporting files related to dataset generation and feature extraction.
Dataset Summary
| Total Number of Features | : 121 |
| Total Number of Instances | : 3,48,47,603 |
| Feature Types | : Integer, Real, Categorical |
| Labels | : label, category, type |
| Missing Values | : None |
Dataset Paper
For more details and citation, refer our paper entitled, "MU-IoT: A new IoT intrusion dataset for network and application layer attacks analysis," IEEE Access 2024.
Download MU-IoT Dataset
Download DatasetAuthors
Contact Information
📍Address: Manipur University, Canchipur-795003, Imphal, Manipur, India
© 2024 Department of Computer Science, Manipur University. All rights reserved.