Implementasi Explainable AI dalam Klasifikasi Kekuatan Password
DOI:
https://doi.org/10.53513/jis.v24i2.12130Keywords:
password, Naive Bayes, explainable AI, SHAP, LIMEAbstract
Keamanan kata sandi (password) merupakan aspek krusial dalam menjaga integritas sistem informasi digital. Namun, banyak pengguna masih menggunakan password yang lemah dan mudah ditebak, sehingga rentan terhadap serangan siber. Penelitian ini bertujuan untuk mengklasifikasikan kekuatan password dan menjelaskan hasil prediksi dengan pendekatan Explainable Artificial Intelligence (XAI), khususnya SHAP (SHapley Additive exPlanations) dan LIME (Local Interpretable Model-agnostic Explanations). Dataset yang digunakan berisi 100.000 password yang telah dilabeli dalam tiga kelas kekuatan password. Proses pra-pemrosesan mencakup ekstraksi fitur berbasis struktur karakteristik password, seperti panjang, huruf besar, angka, dan karakter spesial. Model Naive Bayes yang dibangun menunjukkan performa klasifikasi yang sangat baik dengan skor akurasi: 97,66%, Precision: 94,51%, Recall: 98,23%, dan F1-score: 96,22%. Selanjutnya, analisis XAI dilakukan untuk mengungkap kontribusi fitur terhadap keputusan model, baik secara global maupun lokal. Hasil visualisasi menggunakan SHAP dan LIME menunjukkan bahwa fitur panjang dan keberadaan karakter kapital memberikan pengaruh signifikan terhadap kekuatan password. Selain itu, juga dilakukan interpretasi terhadap prediksi lokal (analisis per-password) sehingga memberikan gambaran kontribusi fitur terhadap setiap kekuatan password. Sebagai implementasi akhir, sebuah antarmuka interaktif berbasis Streamlit dikembangkan untuk memungkinkan pengguna melakukan prediksi dan interpretasi kekuatan password secara real-time.References
M. Yamin, T. T. Malethi, Monica, Jodhika, and S. Natali, “Evaluasi Risiko Pada Penggunaan Password Yang Lemah: Analisis Kasus Penggunaan Password Umum,” J. Ilm. Multidisiplin Ilmu Komput., vol. 1, no. 1, pp. 41–48, 2023, doi: 10.61674/jimik.v1i1.112.
V. Zimmermann, “From the Quest to Replace Passwords towards Supporting Secure and Usable Password Creation,” Technische Universität Darmstadt, Darmstadt, 2021.
Arnah Ritonga et al., “Analisis Kombinatorik Dalam Menentukan Keamanan dan Kompleksitas Password dengan Penerapan Teori Kombinatorik,” Katalis Pendidik. J. Ilmu Pendidik. dan Mat., vol. 2, no. 2 SE-Articles, pp. 49–64, Apr. 2025, doi: 10.62383/katalis.v2i2.1463.
W. Y. Saputra, S. Sugiarti, H. Junianto, and D. Suhartono, “Password Strength Study Using The Zxcvbn Algorithm And Brute-Force Time Estimation To Strengthen Cybersecurity,” J. Pilar Nusa Mandiri, vol. 21, no. 1, pp. 52–59, 2025, doi: 10.33480/pilar.v21i1.6119.
T. Rochmadi, A. Fadlil, and I. Riadi, “Tinjauan Pustaka Sistematis: Tantangan Dan Faktor-Faktor Pengembangan Kesiapan Forensik Digital ,” Cyber Secur. dan Forensik Digit., vol. 7, no. 2 SE-Articles, pp. 81–89, Dec. 2024, doi: 10.14421/csecurity.2024.7.2.4861.
A. Asaduzzaman, D. D’Souza, M. R. Uddin, and Y. Woldeyes, “Increase Security by Analyzing Password Strength using Machine Learning,” in 2024 Joint International Conference on Digital Arts, Media and Technology with ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunications Engineering (ECTI DAMT & NCON), 2024, pp. 32–37, doi: 10.1109/ECTIDAMTNCON60518.2024.10479995.
E. Darbutaitė, P. Stefanovič, and S. Ramanauskaitė, “Machine-Learning-Based Password-Strength-Estimation Approach for Passwords of Lithuanian Context,” Appl. Sci., vol. 13, no. 13, 2023, doi: 10.3390/app13137811.
R. Dwivedi et al., “Explainable AI (XAI): Core Ideas, Techniques, and Solutions,” ACM Comput. Surv., vol. 55, no. 9, Jan. 2023, doi: 10.1145/3561048.
S. M. Lundberg and S.-I. Lee, “A Unified Approach to Interpreting Model Predictions,” in Advances in Neural Information Processing Systems, 2017, vol. 30.
M. T. Ribeiro, S. Singh, and C. Guestrin, “‘Why Should I Trust You?’: Explaining the Predictions of Any Classifier,” in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016, pp. 1135–1144, doi: 10.1145/2939672.2939778.
T. Hulsen, “Explainable Artificial Intelligence (XAI): Concepts and Challenges in Healthcare,” AI, vol. 4, no. 3, pp. 652–666, 2023, doi: 10.3390/ai4030034.
J. Černevičienė and A. Kabašinskas, “Explainable artificial intelligence (XAI) in finance: a systematic literature review,” Artif. Intell. Rev., vol. 57, no. 8, p. 216, 2024, doi: 10.1007/s10462-024-10854-8.
C. Trivedi et al., “Explainable AI for Industry 5.0: Vision, Architecture, and Potential Directions,” IEEE Open J. Ind. Appl., vol. 5, pp. 177–208, 2024, doi: 10.1109/OJIA.2024.3399057.
Q. Liu, J. D. Pinto, and L. Paquette, “Applications of Explainable AI (XAI) in Education,” in Trust and Inclusion in AI-Mediated Education: Where Human Learning Meets Learning Machines, D. Kourkoulou, A.-O. (Olnancy) Tzirides, B. Cope, and M. Kalantzis, Eds. Cham: Springer Nature Switzerland, 2024, pp. 93–109.
A. Dovier, T. Dreossi, and A. Formisano, “XAI-LAW Towards a logic programming tool for taking and explaining legal decisions,” CEUR Workshop Proc., vol. 3733, 2024.
A. S. Yazid, “Eksplorasi Data Akademik untuk Memprediksi Ketepatan Waktu Lulus Mahasiswa Menggunakan Algoritma Naive Bayes,” Jatisi, vol. 11, no. 4, pp. 558–568, 2024.
M. Khorasani, M. Abdou, and J. Hernández Fernández, “Getting Started with Streamlit BT - Web Application Development with Streamlit: Develop and Deploy Secure and Scalable Web Applications to the Cloud Using a Pure Python Framework,” M. Khorasani, M. Abdou, and J. Hernández Fernández, Eds. Berkeley, CA: Apress, 2022, pp. 1–30.
K. Maxim, “Password Security: Sber Dataset,” Kaggle, 2022. [Online]. Available: https://www.kaggle.com/datasets/morph1max/password-security-sber-dataset/. [Accessed: 19-Apr-2025].
N. R. Dzakiyullah, M. A. Burhanuddin, R. R. Raja Ikram, N. Yudistira, M. R. Fauzi, and D. Purbohadi, “Multi-Label Risk Prediction Diabetes Complication Using Machine Learning Models,” Int. J. Online Biomed. Eng., vol. 20, no. 16 SE-Papers, pp. 66–88, Dec. 2024, doi: 10.3991/ijoe.v20i16.51643.
S. Sarkar and M. Nandan, “Password Strength Analysis and its Classification by Applying Machine Learning Based Techniques,” in 2022 Second International Conference on Computer Science, Engineering and Applications (ICCSEA), 2022, pp. 1–5, doi: 10.1109/ICCSEA54677.2022.9936117.
S. J. Kim and B. M. Lee, “Multi-Class Classification Prediction Model for Password Strength Based on Deep Learning,” J. Multimed. Inf. Syst., vol. 10, no. 1, pp. 45–52, Mar. 2023, doi: 10.33851/JMIS.2023.10.1.45.
H. Rehman et al., “Password Strength Classification Using Machine Learning Methods,” in 2024 Global Conference on Wireless and Optical Technologies (GCWOT), 2024, pp. 1–7, doi: 10.1109/GCWOT63882.2024.10805622.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Nama dan alamat email yang masuk ke situs jurnal ini akan digunakan secara eksklusif untuk tujuan jurnal ini dan tidak akan digunakan untuk tujuan dan pihak lain.
