Claim Missing Document
Check
Articles

Found 3 Documents
Search

SELEKSI FITUR MENGGUNAKAN MUTUAL INFORMATION UNTUK DETEKSI INTRUSI Riki Andri Yusda; Sahren Sahren; Mustika Fitri Larasati Sibuea; Nadira Meutia Arifin; Bima Aditya
JOURNAL OF SCIENCE AND SOCIAL RESEARCH Vol. 8 No. 3 (2025): August 2025
Publisher : Smart Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54314/jssr.v8i3.3112

Abstract

Abstract: This study explores the use of Mutual Information (MI) for feature selection in intrusion detection, focusing on the CICIDS 2017 dataset. Given the complexity and large volume of data in intrusion detection systems, this research aims to identify the most informative features. The methodology includes data preprocessing, MI calculation, and feature selection based on the highest MI values. The analysis results indicate that using MI contributes to improving model accuracy and reducing the false positive rate. These findings underscore the importance of feature selection in enhancing the effectiveness of intrusion detection systems and provide significant contributions to developing more efficient cybersecurity strategies. Keyword: IDS, Mutual Information, CICIDS2017, Feature selection Abstrak: Penelitian ini mengeksplorasi penggunaan Mutual Information (MI) untuk seleksi fitur dalam deteksi intrusi, dengan fokus pada dataset CICIDS 2017. Mengingat kompleksitas dan volume data yang besar dalam sistem deteksi intrusi, penelitian ini bertujuan untuk mengidentifikasi fitur-fitur yang paling informatif. Metodologi yang diterapkan mencakup preprocessing data, perhitungan MI, dan seleksi fitur berdasarkan nilai MI tertinggi. Hasil analisis menunjukkan bahwa penggunaan MI berkontribusi pada peningkatan akurasi model serta pengurangan tingkat false positive. Temuan ini menegaskan pentingnya seleksi fitur dalam meningkatkan efektivitas sistem deteksi intrusi dan memberikan kontribusi signifikan dalam pengembangan strategi keamanan siber yang lebih efisien. Kata kunci: IDS, Mutual Information, CICIDS2017, Seleksi fitur
DETEKSI ZERO-DAY SOCIAL ENGINERING ATTACK MENGGUNAKAN NLP DAN OPEN-SET DEEP LEARNING Sahren Sahren; Ruri Ashari Dalimunthe; Bima Aditya
JOURNAL OF SCIENCE AND SOCIAL RESEARCH Vol. 9 No. 2 (2026): April 2026
Publisher : Smart Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54314/jssr.v9i2.6120

Abstract

Text based social engineering attacks are a growing cyber threat that is difficult to detect by conventional intrusion detection systems, especially in previously unobserved or zero-day variants. This study proposes a Natural Language Processing Open-Set Intrusion Detection System (NLP-OSIDS) framework that integrates Term Frequency-Inverse Document Frequency (TF-IDF) trigram (1.3-gram) feature representation with an Open-Set Multilayer Perceptron architecture based on energy based scoring to detect zero-day social engineering attacks without requiring training examples from that class. Experiments were conducted on the public dataset phishing_email.csv with 82,486 combined samples from Enron, SpamAssassin, Nazario, Ling, CEAS, and Nigerian Fraud datasets with strict zero-day partitioning following open-set recognition evaluation standards. The results show that NLP-OSIDS achieved an AUROC of 0.7808, surpassing all closed-set baselines (AUROC = 0.500) with the lowest False Positive Rate of 0.0088, while the Zero-Day Detection Rate (ZD-DR) of 0.077 indicates the need for adaptive threshold optimization as a direction for further research.
PENGENALAN PEMANFAATAN TEKNOLOGI INTERNET OF THINGS (IoT) BAGI SISWA SISWI SMA NEGERI 1 AIR JOMAN Riki Andri Yusda; Sahren Sahren; Junaidi Sholat; Bima Aditya; Muhammad Rafly
Jurnal Pemberdayaan Sosial dan Teknologi Masyarakat Vol. 5 No. 1 (2025): April 2025
Publisher : Smart Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54314/jpstm.v5i1.2924

Abstract

Abstract: The internet has transformed not only data exchange through standard devices such as PCs, laptops, or smartphones, but also shifted to various tools in our surroundings. This concept is known as the Internet of Things (IoT). IoT is defined as a system consisting of networks of sensors, actuators, and smart objects aimed at connecting all items, including everyday objects and those used in industry, making them intelligent, programmable, and capable of interacting with humans. IoT has been widely implemented in various sectors, such as smart cities, innovative healthcare, smart agriculture, smart education, and others. Introducing IoT at an early age, particularly in high schools, is essential, with the hope of fostering students' interest in this field. In this community service initiative, IoT technology was introduced at SMA Negeri 1 Air Joman, by delivering materials on IoT technology and its applications.Keywords: high school, IoT. Abstrak: Penggunaan internet telah mengalami transformasi, tidak hanya untuk pertukaran data melalui perangkat umum seperti PC, laptop, atau smartphone, tetapi juga beralih ke berbagai alat yang ada di sekitar kita. Konsep ini dikenal sebagai Internet of Things (IoT). IoT didefinisikan sebagai sistem yang terdiri dari jaringan sensor, aktuator, dan objek pintar yang bertujuan untuk menghubungkan semua barang, termasuk objek sehari-hari dan yang digunakan dalam industri, sehingga menjadikannya pintar, dapat diprogram, dan mampu berinteraksi dengan manusia. IoT telah banyak diterapkan di berbagai sektor, seperti kota pintar, kesehatan pintar, pertanian pintar, pendidikan pintar, dan bidang lainnya. Pengenalan IoT perlu dilakukan sejak dini, terutama di sekolah menengah atas, dengan harapan dapat meningkatkan minat siswa untuk mendalami bidang ini. Dalam pengabdian masyarakat ini, dilakukan pengenalan teknologi IoT di SMA Negeri 1 Air Joman, melalui penyampaian materi tentang teknologi IoT dan aplikasinya.Kata kunci: IoT, SMA.