AUTENTIKASI BERKELANJUTAN BERBASIS POLA KEYSTROKE MENGGUNAKAN METODE DEEP LEARNING
Isi Artikel Utama
Abstrak
Penelitian ini mengembangkan sistem autentikasi berkelanjutan berbasis pola pengetikan untuk meningkatkan keamanan identitas digital. Permasalahan muncul karena autentikasi konvensional hanya memverifikasi pengguna di awal sesi sehingga rentan terhadap penyusupan. Pendekatan yang digunakan memanfaatkan dinamika pengetikan pada teks bebas dengan menganalisis waktu tekan tombol, jeda antar tombol, dan kecepatan mengetik sebagai biometrik perilaku. Data diproses melalui normalisasi, segmentasi berbasis jendela geser, ekstraksi fitur, pelatihan model pembelajaran mendalam gabungan Convolutional Neural Network dan Bidirectional Long Short-Term Memory, serta evaluasi menggunakan tingkat penerimaan salah, penolakan salah, dan kesalahan seimbang. Hasil menunjukkan sistem mampu mendeteksi identitas pengguna secara konsisten dengan akurasi tinggi, respons cepat, dan kesalahan rendah. Penelitian ini menyimpulkan bahwa autentikasi berbasis dinamika pengetikan efektif sebagai solusi keamanan adaptif, efisien, dan non intrusif.
Rincian Artikel
Sitasi
Haryanto, D. (2026). AUTENTIKASI BERKELANJUTAN BERBASIS POLA KEYSTROKE MENGGUNAKAN METODE DEEP LEARNING. KHARISMA Tech, 21(1), 179-187. https://doi.org/10.55645/kharismatech.v21i1.692
Bagian
Articles
Referensi
[1] Sanam Bhardwaj dan Mayank Dave, “Enhanced neural network-based attack investigation framework for network forensics: Identification, detection, and analysis of the attack,” ScienceDirect, vol. 135, Des 2023, doi: https://doi.org/10.1016/j.cose.2023.103521.
[2] A. T. Kiyani, A. Lasebae, K. Ali, M. U. Rehman, dan B. Haq, “Continuous User Authentication Featuring Keystroke Dynamics Based on Robust Recurrent Confidence Model and Ensemble Learning Approach,” IEEE Access, vol. 8, hlm. 156177–156189, 2020, doi: 10.1109/ACCESS.2020.3019467.
[3] L. Yang, C. Li, R. You, B. Tu, dan L. Li, “TKCA: a timely keystroke-based continuous user authentication with short keystroke sequence in uncontrolled settings,” Cybersecurity, vol. 4, no. 1, Des 2021, doi: 10.1186/s42400-021-00075-9.
[4] P. E. Yunanto dan A. M. Barmawi, “Bimodal Keystroke Dynamics-Based Authentication for Mobile Application Using Anagram,” Jurnal Ilmu Komputer dan Informasi, vol. 15, no. 2, hlm. 81–91, Jul 2022, doi: 10.21609/jiki.v15i2.1015.
[5] C. R. P. Siahaan dan A. Chowanda, “Spoofing keystroke dynamics authentication through synthetic typing pattern extracted from screen-recorded video,” J. Big Data, vol. 9, no. 1, Des 2022, doi: 10.1186/s40537-022-00662-8.
[6] E. A. Sağbaş dan S. Ballı, “Machine learning-based novel continuous authentication system using soft keyboard typing behavior and motion sensor data,” Neural Comput. Appl., vol. 36, no. 10, hlm. 5433–5445, Apr 2024, doi: 10.1007/s00521-023-09360-9.
[7] D. S. Azhari, M. Kustati, dan N. Sepriyanti, “Penelitian Ilmiah (Kuantitatif) Beserta Paradigma, Pendekatan, Asumsi Dasar, Karakteristik, Metode Analisis Data Dan Outputnya.”
[8] Xin-Jin Kek, Yu-Beng Leau, dan Soo Fun Tan, “User Authentication with Keystroke Dynamics: Performance Evaluation in Neural Network,” IEEE , hlm. 30–35, Agu 2024.
[9] N. Altwaijry, “Keystroke Dynamics Analysis for User Authentication Using a Deep Learning Approach,” IJCSNS International Journal of Computer Science and Network Security, vol. 20, no. 12, 2020, doi: 10.22937/IJCSNS.2020.20.12.23.
[10] X. Chen, G. Chuai, dan W. Gao, “Multi-Agent Reinforcement Learning Based Fully Decentralized Dynamic Time Division Configuration for 5G and B5G Network,” Sensors, vol. 22, no. 5, Mar 2022, doi: 10.3390/s22051746.
[11] X. Lu, S. Zhang, P. Hui, dan P. Lio, “Continuous authentication by free-text keystroke based on CNN and RNN,” Comput. Secur., vol. 96, Sep 2020, doi: 10.1016/j.cose.2020.101861.
[12] M. Munandar, A. Rahman Hakim, T. Persandian, dan S. H. Tinggi Sandi Negara Jalan Usa Raya, “ANALISIS KEAMANAN PAIR BASED TEXT AUTHENTICATION PADA SKEMA LOGIN.”
[13] A. Arsh, N. Kar, S. Das, dan S. Deb, “Multiple Approaches Towards Authentication Using Keystroke Dynamics,” dalam Procedia Computer Science, Elsevier B.V., 2024, hlm. 2609–2618. doi: 10.1016/j.procs.2024.04.246.
[14] S. M. Khalil, H. Bahsi, dan T. Korõtko, “Threat modeling of industrial control systems: A systematic literature review,” Comput. Secur., vol. 136, Jan 2024, doi: 10.1016/j.cose.2023.103543.
[15] N. Rochmawati dkk., “Analisa Learning rate dan Batch size Pada Klasifikasi Covid Menggunakan Deep learning dengan Optimizer Adam.”
[1] Sanam Bhardwaj dan Mayank Dave, “Enhanced neural network-based attack investigation framework for network forensics: Identification, detection, and analysis of the attack,” ScienceDirect, vol. 135, Des 2023, doi: https://doi.org/10.1016/j.cose.2023.103521.
[2] A. T. Kiyani, A. Lasebae, K. Ali, M. U. Rehman, dan B. Haq, “Continuous User Authentication Featuring Keystroke Dynamics Based on Robust Recurrent Confidence Model and Ensemble Learning Approach,” IEEE Access, vol. 8, hlm. 156177–156189, 2020, doi: 10.1109/ACCESS.2020.3019467.
[3] L. Yang, C. Li, R. You, B. Tu, dan L. Li, “TKCA: a timely keystroke-based continuous user authentication with short keystroke sequence in uncontrolled settings,” Cybersecurity, vol. 4, no. 1, Des 2021, doi: 10.1186/s42400-021-00075-9.
[4] P. E. Yunanto dan A. M. Barmawi, “Bimodal Keystroke Dynamics-Based Authentication for Mobile Application Using Anagram,” Jurnal Ilmu Komputer dan Informasi, vol. 15, no. 2, hlm. 81–91, Jul 2022, doi: 10.21609/jiki.v15i2.1015.
[5] C. R. P. Siahaan dan A. Chowanda, “Spoofing keystroke dynamics authentication through synthetic typing pattern extracted from screen-recorded video,” J. Big Data, vol. 9, no. 1, Des 2022, doi: 10.1186/s40537-022-00662-8.
[6] E. A. Sağbaş dan S. Ballı, “Machine learning-based novel continuous authentication system using soft keyboard typing behavior and motion sensor data,” Neural Comput. Appl., vol. 36, no. 10, hlm. 5433–5445, Apr 2024, doi: 10.1007/s00521-023-09360-9.
[7] D. S. Azhari, M. Kustati, dan N. Sepriyanti, “Penelitian Ilmiah (Kuantitatif) Beserta Paradigma, Pendekatan, Asumsi Dasar, Karakteristik, Metode Analisis Data Dan Outputnya.”
[8] Xin-Jin Kek, Yu-Beng Leau, dan Soo Fun Tan, “User Authentication with Keystroke Dynamics: Performance Evaluation in Neural Network,” IEEE , hlm. 30–35, Agu 2024.
[9] N. Altwaijry, “Keystroke Dynamics Analysis for User Authentication Using a Deep Learning Approach,” IJCSNS International Journal of Computer Science and Network Security, vol. 20, no. 12, 2020, doi: 10.22937/IJCSNS.2020.20.12.23.
[10] X. Chen, G. Chuai, dan W. Gao, “Multi-Agent Reinforcement Learning Based Fully Decentralized Dynamic Time Division Configuration for 5G and B5G Network,” Sensors, vol. 22, no. 5, Mar 2022, doi: 10.3390/s22051746.
[11] X. Lu, S. Zhang, P. Hui, dan P. Lio, “Continuous authentication by free-text keystroke based on CNN and RNN,” Comput. Secur., vol. 96, Sep 2020, doi: 10.1016/j.cose.2020.101861.
[12] M. Munandar, A. Rahman Hakim, T. Persandian, dan S. H. Tinggi Sandi Negara Jalan Usa Raya, “ANALISIS KEAMANAN PAIR BASED TEXT AUTHENTICATION PADA SKEMA LOGIN.”
[13] A. Arsh, N. Kar, S. Das, dan S. Deb, “Multiple Approaches Towards Authentication Using Keystroke Dynamics,” dalam Procedia Computer Science, Elsevier B.V., 2024, hlm. 2609–2618. doi: 10.1016/j.procs.2024.04.246.
[14] S. M. Khalil, H. Bahsi, dan T. Korõtko, “Threat modeling of industrial control systems: A systematic literature review,” Comput. Secur., vol. 136, Jan 2024, doi: 10.1016/j.cose.2023.103543.
[15] N. Rochmawati dkk., “Analisa Learning rate dan Batch size Pada Klasifikasi Covid Menggunakan Deep learning dengan Optimizer Adam.”
[16] “CNN Algorithm Optimization for Caries Tooth Identification using Adam, Adamax, and RMSprop Optimizer”.
[17] H. Schwenk, L. Barrault, F. Bougares, dan L. Lo¨ıc Barrault, “Efficient Training Strategies for Deep Neural Network Language Models,” 2014. [Daring]. Tersedia pada: https://www.researchgate.net/publication/283354668
[18] Haimin Zhu, Qingzhang Chen, Li Zhang, Miaomiao Li, dan Rupeng Zhu, “Dynamics simulation-based deep residual neural networks to detect flexible shafting faults,” ScienceDirect, vol. 278, Okt 2023.
[19] V. Mingote, A. Miguel, D. Ribas, A. Ortega, dan E. Lleida, “Optimization of false acceptance/rejection rates and decision threshold for end-to-end text-dependent speaker verification systems,” dalam Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, International Speech Communication Association, 2019, hlm. 2903–2907. doi: 10.21437/Interspeech.2019-2550.
[20] W. A. Yasodya dkk., “Self-Adaptive Deep Learning Framework for Non-Intrusive Load Monitoring: Addressing Aging Appliance Challenges with Transfer Learning and Pseudo Labeling”, doi: 10.1109/ACCESS.2024.0429000.
[2] A. T. Kiyani, A. Lasebae, K. Ali, M. U. Rehman, dan B. Haq, “Continuous User Authentication Featuring Keystroke Dynamics Based on Robust Recurrent Confidence Model and Ensemble Learning Approach,” IEEE Access, vol. 8, hlm. 156177–156189, 2020, doi: 10.1109/ACCESS.2020.3019467.
[3] L. Yang, C. Li, R. You, B. Tu, dan L. Li, “TKCA: a timely keystroke-based continuous user authentication with short keystroke sequence in uncontrolled settings,” Cybersecurity, vol. 4, no. 1, Des 2021, doi: 10.1186/s42400-021-00075-9.
[4] P. E. Yunanto dan A. M. Barmawi, “Bimodal Keystroke Dynamics-Based Authentication for Mobile Application Using Anagram,” Jurnal Ilmu Komputer dan Informasi, vol. 15, no. 2, hlm. 81–91, Jul 2022, doi: 10.21609/jiki.v15i2.1015.
[5] C. R. P. Siahaan dan A. Chowanda, “Spoofing keystroke dynamics authentication through synthetic typing pattern extracted from screen-recorded video,” J. Big Data, vol. 9, no. 1, Des 2022, doi: 10.1186/s40537-022-00662-8.
[6] E. A. Sağbaş dan S. Ballı, “Machine learning-based novel continuous authentication system using soft keyboard typing behavior and motion sensor data,” Neural Comput. Appl., vol. 36, no. 10, hlm. 5433–5445, Apr 2024, doi: 10.1007/s00521-023-09360-9.
[7] D. S. Azhari, M. Kustati, dan N. Sepriyanti, “Penelitian Ilmiah (Kuantitatif) Beserta Paradigma, Pendekatan, Asumsi Dasar, Karakteristik, Metode Analisis Data Dan Outputnya.”
[8] Xin-Jin Kek, Yu-Beng Leau, dan Soo Fun Tan, “User Authentication with Keystroke Dynamics: Performance Evaluation in Neural Network,” IEEE , hlm. 30–35, Agu 2024.
[9] N. Altwaijry, “Keystroke Dynamics Analysis for User Authentication Using a Deep Learning Approach,” IJCSNS International Journal of Computer Science and Network Security, vol. 20, no. 12, 2020, doi: 10.22937/IJCSNS.2020.20.12.23.
[10] X. Chen, G. Chuai, dan W. Gao, “Multi-Agent Reinforcement Learning Based Fully Decentralized Dynamic Time Division Configuration for 5G and B5G Network,” Sensors, vol. 22, no. 5, Mar 2022, doi: 10.3390/s22051746.
[11] X. Lu, S. Zhang, P. Hui, dan P. Lio, “Continuous authentication by free-text keystroke based on CNN and RNN,” Comput. Secur., vol. 96, Sep 2020, doi: 10.1016/j.cose.2020.101861.
[12] M. Munandar, A. Rahman Hakim, T. Persandian, dan S. H. Tinggi Sandi Negara Jalan Usa Raya, “ANALISIS KEAMANAN PAIR BASED TEXT AUTHENTICATION PADA SKEMA LOGIN.”
[13] A. Arsh, N. Kar, S. Das, dan S. Deb, “Multiple Approaches Towards Authentication Using Keystroke Dynamics,” dalam Procedia Computer Science, Elsevier B.V., 2024, hlm. 2609–2618. doi: 10.1016/j.procs.2024.04.246.
[14] S. M. Khalil, H. Bahsi, dan T. Korõtko, “Threat modeling of industrial control systems: A systematic literature review,” Comput. Secur., vol. 136, Jan 2024, doi: 10.1016/j.cose.2023.103543.
[15] N. Rochmawati dkk., “Analisa Learning rate dan Batch size Pada Klasifikasi Covid Menggunakan Deep learning dengan Optimizer Adam.”
[1] Sanam Bhardwaj dan Mayank Dave, “Enhanced neural network-based attack investigation framework for network forensics: Identification, detection, and analysis of the attack,” ScienceDirect, vol. 135, Des 2023, doi: https://doi.org/10.1016/j.cose.2023.103521.
[2] A. T. Kiyani, A. Lasebae, K. Ali, M. U. Rehman, dan B. Haq, “Continuous User Authentication Featuring Keystroke Dynamics Based on Robust Recurrent Confidence Model and Ensemble Learning Approach,” IEEE Access, vol. 8, hlm. 156177–156189, 2020, doi: 10.1109/ACCESS.2020.3019467.
[3] L. Yang, C. Li, R. You, B. Tu, dan L. Li, “TKCA: a timely keystroke-based continuous user authentication with short keystroke sequence in uncontrolled settings,” Cybersecurity, vol. 4, no. 1, Des 2021, doi: 10.1186/s42400-021-00075-9.
[4] P. E. Yunanto dan A. M. Barmawi, “Bimodal Keystroke Dynamics-Based Authentication for Mobile Application Using Anagram,” Jurnal Ilmu Komputer dan Informasi, vol. 15, no. 2, hlm. 81–91, Jul 2022, doi: 10.21609/jiki.v15i2.1015.
[5] C. R. P. Siahaan dan A. Chowanda, “Spoofing keystroke dynamics authentication through synthetic typing pattern extracted from screen-recorded video,” J. Big Data, vol. 9, no. 1, Des 2022, doi: 10.1186/s40537-022-00662-8.
[6] E. A. Sağbaş dan S. Ballı, “Machine learning-based novel continuous authentication system using soft keyboard typing behavior and motion sensor data,” Neural Comput. Appl., vol. 36, no. 10, hlm. 5433–5445, Apr 2024, doi: 10.1007/s00521-023-09360-9.
[7] D. S. Azhari, M. Kustati, dan N. Sepriyanti, “Penelitian Ilmiah (Kuantitatif) Beserta Paradigma, Pendekatan, Asumsi Dasar, Karakteristik, Metode Analisis Data Dan Outputnya.”
[8] Xin-Jin Kek, Yu-Beng Leau, dan Soo Fun Tan, “User Authentication with Keystroke Dynamics: Performance Evaluation in Neural Network,” IEEE , hlm. 30–35, Agu 2024.
[9] N. Altwaijry, “Keystroke Dynamics Analysis for User Authentication Using a Deep Learning Approach,” IJCSNS International Journal of Computer Science and Network Security, vol. 20, no. 12, 2020, doi: 10.22937/IJCSNS.2020.20.12.23.
[10] X. Chen, G. Chuai, dan W. Gao, “Multi-Agent Reinforcement Learning Based Fully Decentralized Dynamic Time Division Configuration for 5G and B5G Network,” Sensors, vol. 22, no. 5, Mar 2022, doi: 10.3390/s22051746.
[11] X. Lu, S. Zhang, P. Hui, dan P. Lio, “Continuous authentication by free-text keystroke based on CNN and RNN,” Comput. Secur., vol. 96, Sep 2020, doi: 10.1016/j.cose.2020.101861.
[12] M. Munandar, A. Rahman Hakim, T. Persandian, dan S. H. Tinggi Sandi Negara Jalan Usa Raya, “ANALISIS KEAMANAN PAIR BASED TEXT AUTHENTICATION PADA SKEMA LOGIN.”
[13] A. Arsh, N. Kar, S. Das, dan S. Deb, “Multiple Approaches Towards Authentication Using Keystroke Dynamics,” dalam Procedia Computer Science, Elsevier B.V., 2024, hlm. 2609–2618. doi: 10.1016/j.procs.2024.04.246.
[14] S. M. Khalil, H. Bahsi, dan T. Korõtko, “Threat modeling of industrial control systems: A systematic literature review,” Comput. Secur., vol. 136, Jan 2024, doi: 10.1016/j.cose.2023.103543.
[15] N. Rochmawati dkk., “Analisa Learning rate dan Batch size Pada Klasifikasi Covid Menggunakan Deep learning dengan Optimizer Adam.”
[16] “CNN Algorithm Optimization for Caries Tooth Identification using Adam, Adamax, and RMSprop Optimizer”.
[17] H. Schwenk, L. Barrault, F. Bougares, dan L. Lo¨ıc Barrault, “Efficient Training Strategies for Deep Neural Network Language Models,” 2014. [Daring]. Tersedia pada: https://www.researchgate.net/publication/283354668
[18] Haimin Zhu, Qingzhang Chen, Li Zhang, Miaomiao Li, dan Rupeng Zhu, “Dynamics simulation-based deep residual neural networks to detect flexible shafting faults,” ScienceDirect, vol. 278, Okt 2023.
[19] V. Mingote, A. Miguel, D. Ribas, A. Ortega, dan E. Lleida, “Optimization of false acceptance/rejection rates and decision threshold for end-to-end text-dependent speaker verification systems,” dalam Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, International Speech Communication Association, 2019, hlm. 2903–2907. doi: 10.21437/Interspeech.2019-2550.
[20] W. A. Yasodya dkk., “Self-Adaptive Deep Learning Framework for Non-Intrusive Load Monitoring: Addressing Aging Appliance Challenges with Transfer Learning and Pseudo Labeling”, doi: 10.1109/ACCESS.2024.0429000.