Behavior-based User Authentication Dataset

Description: The behavior-based user authentication dataset is collected from the smart user authentication system through daily activities leveraging commodity WiFi. The dataset contains the extracted CSI features from 8 walking activities and 9 stationary activities from 11 and 5 volunteers, respectively. The experiments are conducted in 2 different environments, including a university office and an apartment. We hope this dataset will help researchers to reproduce the former work of user authentication through WiFi sensing. Dataset Format: .dat files Section 1: Device Configuration: Transmitter: Intel 5300 NIC with a Dell E6430 laptop for control. Receiver: Intel 5300 NIC with a Lenovo T61 laptop for control. Run with a Linux 14.04 operating system with 4.2.0 kernel. Equipped with 3 MINI PCI-E internal antennas. Intel 5300 network interface card (NIC) for CSI collection. The detail information regarding the CSI tool can be found at https://dhalperi.github.io/linux-80211n-csitool/faq.html. WiFi Packet Rate: 1000 pkts/s Section 2: Data Format We provide raw data received by the CSI tool. The data files are saved in the dat format. The details are shown in the following: 8 walking activities and 8 stationary activities are collected from 11 and 5 participants are from two different experiments. Each data file contains 30 rounds of one type of activity from each participant. The dataset file name is presented as " Day_Channel_User_Action ". The detailed information as: Day: The exact date this data was collected. User: The participants that CSI was collected from. Channel: The specific WiFi channel data was collected from. Action: The specific activity performed. Section 3: Experimental Setups There are 2 different experiment setups, including a university office and an apartment environment, for our data collection. The detailed setups are shown in the paper. For the activities, we involve 8 walking activities and 8 stationary activities. An image of the experimental setup and the illustration of activities from two different environments is included in the dataset. Environments: 2 different environments are involved, including an office environment with the size of 26 ft × 14 ft and an apartment with the size of 36 ft × 22 ft. Activity description: A total of 8 walking activities and 8 stationary activities (30 rounds for each) are performed by 11 and 5 volunteers. The walking activities include 8 different trajectories of walking. The stationary activities include 8 daily activities, such as typing on the keyboard, turning on the light, opening the cabinet, fetching documents, eating, opening the oven, opening the fridge and opening the door. Detailed daily activities performed Code Walking activity Code Stationary activity A Entrance ⇒ Seat a Working (i.e., typing keyboard) B Seat ⇒ Entrance b Turning on the light C Seat ⇒ Light Switch c Opening the cabinet D Light Switch ⇒ Seat d Fetching documents E Seat ⇒ Cabinet e Eating at the table F Cabinet ⇒ Seat f Opening the microwave oven G Entrance ⇒ Kitchen g Opening the refrigerator H Kitchen ⇒ Entrance h Opening the door Number of data samples: In total, 3335 activity segments are performed by 11 subjects in the office. 834 activity segments are performed by 5 subjects in the apartment. Section 4: Data Description We separate our raw data into different folders based on different environment types. In each environment type, data are further distributed in terms of date. Each file includes all data from three internal antennas. All data files are in .dat format. We also provide Matlab scripts for CSI analysis and visualization. The following variables can be revealed from the codes: CSI: This is the Channel State Information (CSI) received from one receiver antenna. It describes the signal propagation from the transmitter to the receiver, and it is very sensitive to the impact of environmental changes. Each data reveals CSI from 30 subcarriers. Relative Phase: Relative Phase is a measurement to describe the degree of synchronization between data received from different antennas. It can be used to determine the phase offset for further signal preprocessing. Time: This is the time interval in which the data file contains. It measures time by the number of seconds. It can be used to determine how long the signal has been received. Section 5: Codes analysis_spectrogram.m: load a .dat file and extract all data based on the “Data description” (I.e, CSI, and Relative Phase). Section 6: Citations If your work is related to our work, please cite our papers as follows. https://dl.acm.org/doi/10.1145/3084041.3084061 Cong Shi, Jian Liu, Hongbo Liu, and Yingying Chen. 2017. Smart User Authentication through Actuation of Daily Activities Leveraging WiFi-enabled IoT. In Proceedings of the 18th ACM International Symposium on Mobile Ad Hoc Networking and Computing (Mobihoc '17). Association for Computing Machinery, New York, NY, USA, Article 5, 1–10. Bibtex: @inproceedings{shi2017smart, title={Smart user authentication through actuation of daily activities leveraging WiFi-enabled IoT}, author={Shi, Cong and Liu, Jian and Liu, Hongbo and Chen, Yingying}, booktitle={Proceedings of the 18th ACM International Symposium on Mobile Ad Hoc Networking and Computing}, pages={1--10}, year={2017} }