Analisis Performa Machine Learning Algoritma LightGBM Classifier Pada Malware BIG2015 Menggunakan Metode SMOTE

• SENDI PERMANA
• 14207003

---

ABSTRAK

 

BSTRAK
Nama : Sendi Permana
NIM : 14207003
Program Studi : Ilmu Komputer
Fakultas : Teknologi Informasi
Jenjang : Strata Dua (S2)
Konsentrasi : Data Mining
Judul :“Analisis Performa Machine Learning Algoritma LightGBM
classifier Pada Malware BIG2015 Menggunakan Metode SMOTE”
Malware adalah perangkat lunak berbahaya (virus, worm, trojan horse, spyware,
dll.) yang merusak atau melakukan tindakan berbahaya pada sistem komputer.
Banyak serangan malware muncul di era internet ini, menimbulkan ancaman
keamanan yang serius bagi lembaga keuangan dan pengguna sehari-hari. Ekstraksi
fitur yang efektif dan klasifikasi data malware diperlukan untuk mengatasinya
masalah. Dalam penulisan ini, kami memvisualisasikan virus dalam gambar
sebagaimana adanya menangkap perubahan kecil sambil mempertahankan struktur
global. Tujuan dari penelitian ini adalah untuk bereksperimen dengan menggunakan
Ensemble Learning dan tuning pada dataset Microsoft Malware BIG 2015
Challenge dengan menyediakan metode klasifikasi. kami menerapkan metode
Oversampling SMOTE untuk menyeimbangkan pada kelas dataset tersebut. Hasil
studi pada model tertinggi dengan nilai akurasi sebesar 0.9899, AUC = 0.9997,
Recall = 0.9899, Prec = 0.9901, F1-score = 0.9898 dan Kappa = 0.9877 saat
menggunakan LightGBM untuk analisa performa pada deteksi malware.
Pembelajaran memanfaatkan database Kaggle yang tersedia untuk umum yang
disediakan oleh Microsoft Malware BIG 2015 Challenge(BIG 2015).
Kata Kunci : Malware Detection, LightGBM, Oversampling SMOTE
 

KATA KUNCI

Analisis,Performa Machine Learning,Algoritma Light GBM Classifier

---

DAFTAR PUSTAKA

 

DAFTAR PUSTAKA [1] M. Kalash, M. Rochan, N. Mohammed, N. D. B. Bruce, Y. Wang, and F.
Iqbal, “Malware Classification with Deep Convolutional Neural
Networks,” 2018. [2] M. Programs, V. Salini, P. Davuluru, B. N. Narayanan, and E. J. Balster,
“Convolutional Neural Networks as Classification Tools and Feature
Extractors for Distinguishing,” pp. 273–278, 2019. [3] J. Hemalatha, S. A. Roseline, S. Geetha, and S. Kadry, “An Efficient DenseNet-Based Deep Learning Model for Malware Detection,” pp. 1 –23, 2021. [4] D. R. Akbi and A. R. Rosyadi, “Analisis klasterisasi malware: evaluasi data
training dalam proses klasifikasi malware,” vol. 2, no. 2, pp. 58–66, 2018. [5] S. S. Hansen, T. Mark, T. Larsen, M. Stevanovic, and J. M. Pedersen, “An Approach for Detection and Family Classification of Malware Based on
Behavioral Analysis,” 2016. [6] Y. W. Sitorus, P. Sukarno, and S. Mandala, “Analisis Deteksi Malware Android menggunakan metode Support Vector Machine & Random
Forest,” vol. 8, no. 6, pp. 12500–12518, 2021. [7] J. Saxe, I. Labs, K. Berlin, and I. Labs, “Deep Neural Network Based
Malware Detection Using Two Dimensional Binary Program Features,” 2015. [8] S. Singla, “A Novel Approach to Malware Detection using Static
Classification,” vol. 13, no. 3, pp. 1 –5, 1947. [9] S. K. Sawaisarje, “Malware detection based on string length histogram
using machine learning,” pp. 1836–1841, 2018. [10] A. Javed and M. Akhlaq, “Patterns in Malware Designed for Data
Espionage and Backdoor Creation,” pp. 338–342, 2015. [11] A. Kumar, V. Agarwal, S. K. Shandilya, and A. Shalaginov, “PACER?: Platform for Android Malware Classification , Performance Evaluation and
Threat Reporting †,” pp. 1 –19, 2020, doi: 10.3390/fi12040066. [12] S. Akarsh, K. Simran, P. Poornachandran, V. K. Menon, and K. P. Soman,
“Deep Learning Framework and Visualization for Malware Classification,”
2019 5th Int. Conf. Adv. Comput. Commun. Syst. , pp. 1059–1063, 2019. [13] E. G. Dada, J. S. Bassi, Y. J. Hurcha, and A. H. Alkali, “Performance Evaluation of Machine Learning Algorithms for Detection and Prevention
of Malware Attacks,” vol. 21, no. 3, pp. 18–27, 2019, doi: 10.9790/0661 - 2103011827. [14] G. Shin and M. Han, “Analysis of Feature Importance and Interpretation for Malware Classification Analysis of Feature Importance and
Interpretation for Malware Classification,” no. December, 2020, doi: 10.32604/cmc.2020.010933. [15] J. Moon, S. Kim, J. Song, and K. Kim, “Study on Machine Learning
Techniques for Malware Classification and Detection,” vol. 15, no. 12, pp. 4308–4325, 2021. [16] A. Smote and D. A. N. Neighbor, “KLASIFIKASI DATA TIDAK
SEIMBANG MENGGUNAKAN,” vol. 3, no. 1, pp. 44–49. [17] A. I. Riaddy, Y. Sibaroni, S. Si, A. Aditsania, S. Si, and M. Si, “Ekstraksi
26 Informasi pada Makalah Ilmiah dengan Pendekatan Supervised Learning Information Extraction on Scientific Papers with Supervised Learning
Approach,” vol. 3, no. 1, pp. 1184–1190, 2016. [18] E. Retnoningsih and R. Pramudita, “Mengenal Machine Learning Dengan
Teknik Supervised Dan Unsupervised Learning Menggunakan Python,”
Bina Insa. Ict J., vol. 7, no. 2, p. 156, 2020, doi: 10.51211/biict.v7i2.1422. [19] L. Angelina, Y. Purwanto, A. Novianty, P. S1, and S. Komputer,
“Pengambilan Keputusan Pada Trafik Management Dengan Menggunakan Reinforcement Learning Decision Making on Traffic Management Using
Reinforcement Learning,” vol. 3, no. 3, pp. 4964–4971, 2016. [20] B. Cakir, “Malware Classification Using Deep Learning Methods,” 2018. [21] T. Manyumwa, P. F. Chapita, H. Wu, and S. Ji, “Towards Fighting
Cybercrime?: Malicious URL Attack Type Detection using Multiclass
Classification,” pp. 1813–1822, 2020. [22] J. Teknologi, M. T. Anwar, D. Rianditha, and A. Permana, “Perbandingan Performa Model Data Mining untuk Prediksi Dropout Mahasiwa,” vol. 2, pp. 87–94, 2021, doi: 10.52330/jtm.v19i2.34. [23] F. Bahtiar, N. Widiyasono, and A. P. Aldya, “Memory Volatile Forensik
Untuk Deteksi Malware Menggunakan Algoritma Machine Learning,” vol. 4, pp. 242–253, 2018. [24] V. No and E. L. S, “Klasifikasi Malware Trojan Ransomware Dengan
Algoritma Support Vector Machine ( SVM ),” vol. 2, no. 1, pp. 122–127, 2016. [25] S. R. Wardhana, “Analisa hybrid untuk sistem deteksi malware otomatis dengan support vector model classifier,” pp. 1 –10, 2014. [26] G. A. Sandag, J. Leopold, and V. F. Ong, “Klasifikasi Malicious Websites Menggunakan Algoritma K-NN Berdasarkan Application Layers dan Network Characteristics Malicious Websites Classification Using K-NN Algorithm Based on Application Layers and Network Characteristics,” vol. 4, no. 1, pp. 37–45, 2018. [27] P. Desiana, W. Ayu, and G. A. Pradipta, “Performansi seleksi fitur untuk
mendukung kinerja ann dalam klasifikasi citra sel serviks tunggal,” no. Selisik, pp. 339–344, 2018. [28] A. Maulida, “Penerapan Metode Klasifikasi K-Nearest Neigbor pada
Dataset Penderita Penyakit Diabetes,” vol. 1, no. 2, pp. 29–33, 2020. [29] Y. Pang, L. Peng, Z. Chen, B. Yang, and H. Zhang, “Imbalanced learning based on adaptive weighting and Gaussian function synthesizing with an
application on Android malware detection,” vol. 484, pp. 95–112, 2019, doi: 10.1016/j.ins.2019.01.065. [30] Y. Pang et al., “Finding Android Malware Trace From Highly Imbalanced
Network Traffic,” 2017, doi: 10.1109/CSE-EUC.2017.108. [31] R. Ronen, M. Radu, C. Feuerstein, and E. Yom-tov, “Microsoft Malware
Classification Challenge,” pp. 1 –7, doi: 10.1145/2857705.2857713. [32] B. N. Narayanan, O. Djaneye-Boundjou, and T. M. Kebede, “Performance analysis of machine learning and pattern recognition algorithms for
Malware classification,” Proc. IEEE Natl. Aerosp. Electron. Conf.
NAECON, vol. 0, pp. 338–342, 2016, doi: 10.1109/NAECON.2016.7856826.
27 [33] C. L. A. Ssifier, “No Title,” pp. 89–96. [34] P. Sarker and N. A. Turzo, “Assortment of Bangladeshi E-commerce Site
Reviews using Machine Learning Approaches,” vol. 0, pp. 19–20, 2020. [35] M. Sc, “A MACHINE LEARNING APPROACH FOR SELECTION OF POLYCYSTIC OVARIAN SYNDROME ( PCOS ) ATTRIBUTES AND COMPARING DIFFERENT CLASSIFIER PERFORMANCE WITH THE HELP OF WEKA A .... A MACHINE LEARNING APPROACH FOR SELECTION OF POLYCYSTIC OVARIAN SYNDROME ( PCOS ) ATTRIBUTES AND COMPARING DIFFERENT CLASSIFIER Khandia *
Brijraj Gautam,” no. December, 2020, doi: 10.36106/ijsr/5416514.