AUTENTIKASI BERKELANJUTAN BERBASIS POLA KEYSTROKE MENGGUNAKAN METODE DEEP LEARNING
Main Article Content
Abstract
This study developed a continuous authentication system based on keystroke patterns to enhance digital identity security. The problem arose because conventional authentication only verified users at the beginning of a session, making it vulnerable to session intrusion. The proposed approach utilized free-text keystroke dynamics by analyzing key press duration, inter-key latency, and typing speed as behavioral biometric features. Data were processed through normalization, sliding window segmentation, feature extraction, training of a hybrid deep learning model combining Convolutional Neural Network and Bidirectional Long Short-Term Memory, and evaluation using False Acceptance Rate, False Rejection Rate, and Equal Error Rate. The results showed that the system consistently identified legitimate users with high accuracy, fast detection response, and low error rates. It was concluded that keystroke-based continuous authentication provided an effective, adaptive, efficient, and non-intrusive security solution
Article Details
How to Cite
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
Section
Articles
References
[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.