Klasifikasi Malware Dengan Machine Learning
Abstract
Perkembangan malware yang pesat menjadi tantangan besar bagi keamanan sistem informasi. Berdasarkan data G Data Security Labs, pada 2022 ditemukan lebih dari 50 juta jenis malware baru. Penelitian ini mengimplementasikan tiga algoritma machine learning yaitu Logistic Regression, XGBoost, dan Convolutional Neural Network (CNN) untuk mengklasifikasikan malware melalui analisis data statis. Dataset terdiri dari 130.046 sampel malware dan benign yang diperoleh dari Kaggle serta VirusShare. Proses penelitian meliputi prapemrosesan data, pembagian dataset menjadi 80% data latih dan 20% data uji, pelatihan model, serta evaluasi kinerja menggunakan metrik akurasi, presisi, recall, dan F1-score. Hasil pengujian menunjukkan XGBoost sebagai model dengan performa terbaik dengan akurasi 99,31%, precision 99,30%, recall 99,33%, dan F1-score 99,31%. CNN berada di posisi kedua dengan akurasi 98,89%, precision 98,91%, recall 98,88%, dan F1- score 98,89%. Logistic Regression mencatat akurasi 96,11%, precision 96,07%, recall 96,15%, dan F1-score 96,11%. XGBoost terbukti menjadi model paling efektif dalam klasifikasi malware pada penelitian ini sehingga berpotensi meningkatkan akurasi dan efisiensi sistem deteksi malware. Kata kunci— Machine Learning, Logistic Regression, XGBoost, Convolutional Neural Network , Malware
Downloads
References
[1] W. Satria, J. Prayoga, and E. Dores, “Sosialisasi Keamanan Siber Bagi Pelajar Dalam Menghadapi Era Digital,” Abdi Dalem: Jurnal Pengabdian Kepada Masyarakat, vol. 2, no. 1, pp. 9–17, 2025.
[2] E. S. Alomari, R. R. Nuiaa, Z. A. A. Alyasseri, H. J. Mohammed, N. S. Sani, M. I. Esa, and B. A. Musawi, “Malware detection using deep learning and correlation-based feature selection,” Symmetry, vol. 15, no. 1, p. 123, 2023.
[3] Deep Instinct, “Deep Instinct Reports 358% Increase in Malware Attacks in 2020,” 2021. [Online]. Available: https://www.deepinstinct.com/. [Accessed: Jan. 2, 2025].
[4] P. Maniriho, A. N. Mahmood, and M. J. M. Chowdhury, “A study on malicious software behaviour analysis and detection techniques: Taxonomy, current trends and challenges,” Future Generation Computer Systems, vol. 130, pp. 1–18, 2022.
[5] G Data, “Attacks every few seconds: Around 100 malware variants per minute threaten IT security,” 2023. [Online]. Available: https://presse.gdata.de/news-attacks-every-fewseconds-around-100-malware-variants-per-minute-threatenit-security?id=174381&menueid=28982&l=english. [Accessed: Jan. 2, 2025].
[6] R. Alfred, “The rise of machine learning for big data analytics,” in Proc. 2016 2nd Int. Conf. Science in Information Technology (ICSITech), Balikpapan, 2016, pp. 1–6.
[7] P. Kishore, B. P. Gond, and D. P. Mohapatra, “Enhancing Malware Classification with Machine Learning: A Comparative Analysis of API Sequence-Based Techniques,” in Proc. 2024 IEEE Int. Conf. Smart Power Control and Renewable Energy (ICSPCRE), 2024, pp. 1–6.
[8] A. Almaleh, R. Almushabb, and R. Ogran, “Malware API calls detection using hybrid logistic regression and RNN model,” Applied Sciences, vol. 13, no. 9, p. 5439, 2023.
[9] T. A. Aziz, “Klasifikasi Malware Android Dengan Menggunakan Metode XGBoost Algoritma,” Jurnal Repositor, vol. 7, no. 1, pp. 103–110, 2025.
[10] S. Choudhary and A. Sharma, “Malware detection & classification using machine learning,” in Proc. 2020 Int. Conf. Emerging Trends in Communication, Control and Computing (ICONC3), 2020, pp. 1–4.
[11] U. H. Rao, U. Nayak, U. H. Rao, and U. Nayak, “Malicious software and anti-virus software,” in The InfoSec Handbook: An Introduction to Information Security, 2014, pp. 141–161.
[12] A. H. N. Al-ojaimi, “Advanced Framework for Detecting Malware in Portable Executable (PE) Files Using a MultiModel,” Journal of Information Systems Engineering and Management, vol. 10, no. 36, pp. 769–781, 2025.
[13] H. Cai, J. Cai, and L. Sun, “An adaptive gradient privacypreserving algorithm for federated XGBoost,” in Proc. 2023 2nd Asia Conf. Algorithms, Computing and Machine Learning, 2023, pp. 277–282.
[14] D. Z. Syeda and M. N. Asghar, “Dynamic malware classification and API categorisation of Windows portable executable files using machine learning,” Applied Sciences, vol. 14, no. 3, p. 1015, 2024.
[15] D. Z. Syeda and M. N. Asghar, “Dynamic malware classification and API categorisation of Windows portable executable files using machine learning,” Applied Sciences, vol. 14, no. 3, p. 1015, 2024.
[16] J. F. Balarezo, S. Wang, K. G. Chavez, A. Al-Hourani, and S. Kandeepan, “A survey on DoS/DDoS attacks mathematical modelling for traditional, SDN and virtual networks,” Engineering Science and Technology, an International Journal, vol. 31, p. 101065, 2022.



