GCU Dataset Version 1
GCU dataset version 1 is collected from 7 users consisting of staff and students of Glasgow Caledonian University. The data was collected in 2013 from Android devices and contains sensor data from wifi networks, cell towers, application use, light and sound levels and device system stats. The duration of the data varies from 2 weeks to 14 weeks for different users. Compared to other publicly available datasets used in this paper, it also contains a detailed diary for each user which allows for a detailed investigation of anomalies.
It is currently being used to develop a technique that will allow the device to establish a comfort level with its user, by learning the user behaviour.
A subset of GCU data is made available here in anonymized format. Each file contains the cell tower, wifi network and application captures of a user and has the following format:
- Probe name (GCU.CellProbe, GCU.RunningApplicationsProbe, GCU.WifiProbe)
- List of values (observed by the probe)
The data is provided for research purposes. Reverse engineering and other uses of this data is strictly prohibited. Please treat it as if it is your own daily use data.
If you end up using the dataset in an academic project, please consider citing it as:
- Kayacik H. G., Just M., Baillie L., Aspinall D., Micallef N.,"Data Driven Authentication: On the Effectiveness of User Behaviour Modelling with Mobile Device Sensors", Proceedings of the 3rd Mobile Security Technologies Workshop , Held as part of the IEEE S&P Symposium, (MoST-2014), May 2014.