Identifikasi Pengguna Berbasiskan Biometrik Keystroke Menggunakan MVMCNN
Abstract
Keamanan akses pengguna daring menjadi isu
krusial di era digital. Identifikasi berbasis biometrik, seperti
keystroke dynamics, dianggap lebih aman dibandingkan
metode konvensional. Penelitian ini mengimplementasikan
Multi-Voter Multi-Commission Nearest Neighbor Classifier
(MVMCNN) untuk identifikasi pengguna melalui keystroke
dynamics. MVMCNN dipilih karena kemampuannya mengatasi
kelemahan KNN dengan skema multi-voter dan pendekatan
Local Mean Probabilistic Neural Network (LMPNN). Dataset
keystroke dari Universitas Telkom digunakan dengan fitur UD,
DD, DU, UU, dan Duration. Eksperimen meliputi tiga skenario:
(1) menentukan panjang vektor optimal (N=4, 8, 12, 16, 20, 24),
(2) penyederhanaan fitur menjadi rata-rata dan median, serta
(3) seleksi fitur menggunakan Variance Threshold (0.1).
Evaluasi menggunakan F1-Score. Hasil menunjukkan skenario
pertama dengan N=20 menghasilkan F1-Score tertinggi
(0.6911). Penyederhanaan fitur menurunkan performa, dengan
F1-Score terbaik 0.3031 (mean, k=9) dan 0.3257 (median, k=3),
menandakan pentingnya kekayaan informasi dalam fitur.
Seleksi fitur menggunakan Variance Threshold tidak banyak
mengubah performa, menunjukkan distribusi data sudah
optimal. Temuan ini menegaskan bahwa granularitas data
berperan penting dalam akurasi sistem identifikasi berbasis
keystroke dynamics.
Kata kunci— biometrik, keystroke, identifikasi, mvmcnn, f1-
score.
References
A. Tarter, “Importance of Cyber Security,” in
Community Policing - A European Perspective: Strategies,
Best Practices and Guidelines, R. and A. B. and M. G. Bayerl
P. Saskia and Karlović, Ed., Cham: Springer International
Publishing, 2017, pp. 213–230. doi: 10.1007/978-3-319-
-4_15.
F. Monrose and A. D. Rubin, “Keystroke dynamics
as a biometric for authentication,” Future Generation
Computer Systems, vol. 16, no. 4, pp. 351–359, 2000, doi:
https://doi.org/10.1016/S0167-739X(99)00059- X.
T. Sendjaja, Irwandi, E. Prastiawan, Y. Suryani, and
E. Fatmawati, “Cybersecurity In The Digital Age:
Developing Robust Strategies To Protect Against Evolving
Global Digital Threats And Cyber Attacks,” International
Journal of Science and Society, vol. 6, pp. 1008–1019, Jan.
, doi: 10.54783/ijsoc.v6i1.1098.
R. Verma, “CYBERSECURITY CHALLENGES IN
THE ERA OF DIGITAL TRANSFORMATION,” 2024, p.
doi: 10.25215/9392917848.20.
D. Gunetti and C. Picardi, “Keystroke analysis of free
text,” ACM Trans. Inf. Syst. Secur., vol. 8, no. 3, pp. 312–
, Aug. 2005, doi: 10.1145/1085126.1085129.
A. Jain, P. Flynn, and A. Ross, Handbook of
Biometrics. 2008. doi: 10.1007/978-0-387-71041-9.
I. Tsimperidis, O.-D. Asvesta, E. Vrochidou, and G.
A. Papakostas, “IKDD: A Keystroke Dynamics Dataset for
User Classification,” Information, vol. 15, no. 9, 2024, doi:
3390/info15090511.
B. R. Krishna and M. S. Varma, “Enhancing UserLevel Security: Performance Analysis of Machine Learning
Algorithms for Dynamic Keystroke Analysis,” J Theor Appl
Inf Technol, vol. 101, no. 13, pp. 5313– 5323, 2023, [Online].
Available: http://www.jatit.org
S. Suyanto, P. E. Yunanto, T. Wahyuningrum, and S.
Khomsah, “A multivoter multi-commission nearest neighbor
classifier,” Journal of King Saud University - Computer and
Information Sciences, vol. 34, no. 8, Part B, pp. 6292–6302,
, doi: https://doi.org/10.1016/j.jksuci.2022.01.018.
S. Zhang, “Challenges in KNN Classification,”
IEEE Trans Knowl Data Eng, vol. 34, no. 10, pp. 4663–4675,
Oct. 2022, doi: 10.1109/TKDE.2021.3049250.
Y. Muliono, H. Ham, and D. Darmawan,
“Keystroke Dynamic Classification using Machine Learning
for Password Authorization,” 39 Procedia Comput Sci, vol.
, pp. 564–569, 2018, doi:
https://doi.org/10.1016/j.procs.2018.08.209.
S. Simske, “Dynamic biometrics: The case for a
real-time solution to the problem of access control, privacy
and security,” in 2009 1st IEEE International Conference on
Biometrics, Identity and Security, BIdS 2009, Jan. 2009, pp.
–10. doi: 10.1109/BIDS.2009.5507535.
J. Kim and P. Kang, “Freely typed keystroke
dynamics-based user authentication for mobile devices based
on heterogeneous features,” Pattern Recognit, vol. 108, p.
, 2020, doi:
https://doi.org/10.1016/j.patcog.2020.107556.
S. Uellenbeck, M. Dürmuth, C. Wolf, and T. Holz,
“Quantifying the security of graphical passwords: The case
of Android unlock patterns,” in Proceedings of the ACM
Conference on Computer and Communications Security, Jan.
, pp. 161–172. doi: 10.1145/2508859.2516700.
S. Rane, Y. Wang, S. C. Draper, and P. Ishwar,
“Secure Biometrics: Concepts, Authentication Architectures,
and Challenges,” IEEE Signal Process Mag, vol. 30, no. 5,
pp. 51–64, Sep. 2013, doi: 10.1109/msp.2013.2261691.
