DETEKSI SERANGAN REMOTE CODE EXECUTION DAN CROSS SITE SCRIPTING MENGGUNAKAN MACHINE LEARNING
Abstract
Based on the Annual Report of the Indonesian National Cyber and Crypto Agency for the year 2022, the total number of cyberattacks throughout 2022 nearly reached 976,429,996 attacks. Not only that, but the number of data breaches that occurred in 2022 was also very high, such as: a) 26 million Indihome customer data; b) 17 million PLN customer data; c) 1.3 billion SIM card data; d) 105 million KPU data; and e) 26 million Polri data. Given these issues and as a response to the high level of cyberattacks in Indonesia, research related to attack detection is of high urgency. This research aims to develop a machine learning-based cyberattack detection system. The rapid advancement of technology has made cyberattacks increasingly difficult to detect. The methods and vectors of cyberattacks used are becoming more complex and diverse. Therefore, this research employs machine learning methods for detection. The focus of this study is on two types of cyberattacks: Remote Code Execution and Cross Site Scripting. To obtain an accurate detection model, this research tested three algorithms: a) Support Vector Machine; b) Gradient Boosting; and c) Logistic Regression. Based on the research conducted, the Support Vector Machine algorithm achieved the highest accuracy rate, namely 0.9876 for Remote Code Execution and 0.9961 for Cross Site Scripting. Meanwhile, Logistic Regression achieved accuracy rates of 0.9537 (Remote Code Execution) and 0.9939 (Cross Site Scripting), and Gradient Boosting achieved accuracy rates of 0.9475 (Remote Code Execution) and 0.9939 (Cross Site Scripting).
Keywords
Full Text:
PDFReferences
A. Yusuf, Laporan Tahunan 2020 Honeynet Project BSSN - IHP. Badan Siber dan Sandi Negara, 2022.
S. Parulian, D. A. Pratiwi, dan M. C. Yustina, “Studi Tentang Ancaman dan Solusi Serangan Siber di Indonesia,” Telecommun. Netw. Electron. Comput. Technol. TELNECT, vol. 1, no. 2, Art. no. 2, Des 2021.
“BSSN: Hampir 1 Miliar Serangan Siber Hantam RI di 2022.” Diakses: 9 April 2023. [Daring]. Tersedia pada: https://www.cnnindonesia.com/teknologi/20230119144028-192-902537/bssn-hampir-1-miliar-serangan-siber-hantam-ri-di-2022
K. D. Ayunda, A. Widjajarto, dan A. Budiono, “Implementation and Analysis ModSecurity on Web-Based Application with OWASP Standards,” vol. 8, no. 3, hlm. 12, 2021.
S. -, I. Riadi, dan P. Ananda, “Vulnerability Analysis of E-voting Application using Open Web Application Security Project (OWASP) Framework,” Int. J. Adv. Comput. Sci. Appl., vol. 10, no. 11, 2019, doi: 10.14569/IJACSA.2019.0101118.
G. Nivetha, “IDENTIFYING THE CROSS SITE SCRIPTING (XSS) ATTACK USING XSSER TOOL AND DETECTION USING SUPERVISED LEARNING ALGORITHM,” Ind. Eng. J., no. 1, 2023.
T. Saha, T. Al Rahat, N. Aaraj, Y. Tian, dan N. K. Jha, “ML-FEED: Machine Learning Framework for Efficient Exploit Detection,” dalam 2022 IEEE 4th International Conference on Trust, Privacy and Security in Intelligent Systems, and Applications (TPS-ISA), Des 2022, hlm. 140–149. doi: 10.1109/TPS-ISA56441.2022.00027.
D. A. Prasetio, K. Kusrini, dan M. R. Arief, “Cross-site Scripting Attack Detection Using Machine Learning with Hybrid Features,” J. INFOTEL, vol. 13, no. 1, hlm. 1–6, Feb 2021, doi: 10.20895/infotel.v13i1.606.
S. Abaimov dan G. Bianchi, “CODDLE: Code-Injection Detection With Deep Learning,” IEEE Access, vol. 7, hlm. 128617–128627, 2019, doi: 10.1109/ACCESS.2019.2939870.
A. Bhardwaj, S. S. Chandok, A. Bagnawar, S. Mishra, dan D. Uplaonkar, “Detection of Cyber Attacks: XSS, SQLI, Phishing Attacks and Detecting Intrusion Using Machine Learning Algorithms,” dalam 2022 IEEE Global Conference on Computing, Power and Communication Technologies (GlobConPT), New Delhi, India: IEEE, Sep 2022, hlm. 1–6. doi: 10.1109/GlobConPT57482.2022.9938367.
J. K. Cage, “Python Natural Language Processing (NLP) Exercises : From Basics to BERT,” hlm. 163.
L. Ali, I. Wajahat, N. Amiri Golilarz, F. Keshtkar, dan S. A. C. Bukhari, “LDA–GA–SVM: improved hepatocellular carcinoma prediction through dimensionality reduction and genetically optimized support vector machine,” Neural Comput. Appl., vol. 33, no. 7, hlm. 2783–2792, Apr 2021, doi: 10.1007/s00521-020-05157-2.
R. Sarkhani Benemaran, M. Esmaeili-Falak, dan A. Javadi, “Predicting resilient modulus of flexible pavement foundation using extreme gradient boosting based optimised models,” Int. J. Pavement Eng., vol. 0, no. 0, hlm. 1–20, Jul 2022, doi: 10.1080/10298436.2022.2095385.
F. Handayani, “Komparasi Support Vector Machine, Logistic Regression Dan Artificial Neural Network Dalam Prediksi Penyakit Jantung,” J. Edukasi Dan Penelit. Inform. JEPIN, vol. 7, no. 3, hlm. 329, Des 2021, doi: 10.26418/jp.v7i3.48053.
G. A. Supriatmaja, I. P. M. Y. Pratama, K. Mahendra, I. M. E. Listartha, dan G. A. J. Saskara, “Perbandingan Vulnerability Analysis Pada Website Menggunakan Tools Wapiti, Skipfish, Dan Arachni,” JurTI J. Teknol. Inf., vol. 6, no. 2, Art. no. 2, Des 2022, doi: 10.36294/jurti.v6i2.2990.
Swissky, “Payloads All The Things.” 9 April 2023. Diakses: 9 April 2023. [Daring]. Tersedia pada: https://github.com/swisskyrepo/PayloadsAllTheThings
F. Mereani dan J. Howe, “Exact and Approximate Rule Extraction from Neural Networks with Boolean Features,” dipresentasikan pada 11th International Conference on Neural Computation Theory and Applications, Jul 2022, hlm. 424–433. Diakses: 1 Juli 2022. [Daring]. Tersedia pada: https://www.scitepress.org/Link.aspx?doi=10.5220/0008362904240433
DOI: https://doi.org/10.30873/ji.v23i2.3931
Jurnal Informatika is abstracting and indexing in the following databases:
.png)
JURNAL INFORMATIKA
Dikelola Oleh: Lembaga Penelitian dan Pengabdian kepada Masyarakat (LPPM)
Diterbitkan Oleh: Institut Informatika dan Bisnis Darmajaya
Alamat: Jl. Z.A. Pagar Alam No. 93 Gedong Meneng, Bandar Lampung Lampung
Website: jurnal.darmajaya.ac.id
Email: lp4mjurin@gmail.com
Jurnal Informatika is licensed under a Creative Commons Attribution 4.0 International License.