Online Binary Models are Promising for Distinguishing Temporally Consistent Computer Usage Profiles

@article{Giovanini2022OnlineBM,
  title={Online Binary Models are Promising for Distinguishing Temporally Consistent Computer Usage Profiles},
  author={Luiz H. F. Giovanini and Fabr{\'i}cio Ceschin and Mirela Silva and Aokun Chen and Ramchandra Kulkarni and Sanjay Banda and Madison Lysaght and Heng Qiao and Nikolaos Sapountzis and Ruimin Sun and Brandon Matthews and Dapeng Wu and Andr'e Gr'egio and Daniela Oliveira},
  journal={IEEE Transactions on Biometrics, Behavior, and Identity Science},
  year={2022},
  volume={4},
  pages={412-423}
}
This paper investigates whether computer usage profiles comprised of process-, network-, mouse-, and keystroke-related events are unique and consistent over time in a naturalistic setting, discussing challenges and opportunities of using such profiles in applications of continuous authentication. We collected ecologically-valid computer usage profiles from 31 MS Windows 10 computer users over 8 weeks and submitted this data to comprehensive machine learning analysis involving a diverse set of… 

Figures and Tables from this paper

References

SHOWING 1-10 OF 42 REFERENCES

Study of Intra- and Inter-user Variance in Password Keystroke Dynamics

Overall typing time for a provided password “.tie5Roanl” changes significantly over time, decreasing by almost 30%.

Shared dataset on natural human-computer interaction to support continuous authentication research

A novel large dataset that captures not only keystrokes, but also mouse events and active programs in the case where an intruder takes over an authenticated terminal or simply has access to sign-on credentials is provided.

A practical evaluation of free-text keystroke dynamics

This study presents the first study to evaluate keystroke dynamics while respecting the temporal order of the data, and evaluates the performance of different ways of forming a test sample using sessions, as well as a form of continuous authentication that is based on a sliding window on the keystroke time series.

Characterizing web use on smartphones

Findings are that web page revisitation through browsers occurred very infrequently, bookmarks were used sparingly, physical traversing patterns mirrored virtual (internet) traversing pattern and users systematically differed in their web use.

Continuous Authentication of Smartphones Based on Application Usage

An empirical investigation of active/continuous authentication for smartphones is presented by exploiting users’ unique application usage data, i.e., distinct patterns of use, modeled by a Markovian process, and finds that for enhanced verification performance, unforeseen events should be considered.

Shared keystroke dataset for continuous authentication

This paper provides the details on the collection of a shared dataset for the study of keystroke dynamics and applies an existing algorithm, viz.

Active Authentication on Mobile Devices via Stylometry, Application Usage, Web Browsing, and GPS Location

This paper collects and analyzes behavioral biometrics data from 200 subjects, each using their personal Android mobile device for a period of at least 30 days, and considers four biometric modalities: 1) text entered via soft keyboard, 2) applications used, 3) websites visited, and 4) physical location of the device as determined from GPS or WiFi.

Biometric Recognition Based on Free-Text Keystroke Dynamics

This paper presents a new approach for the free text analysis of keystroke that combines monograph and digraph analysis, and uses a neural network to predict missing digraphs based on the relation between the monitored keystrokes.