Claim Missing Document
Check
Articles

Found 38 Documents
Search

IoT Botnet Detection Using Autoencoders and Decision Trees Susanto, Susanto; Arifin, M. Agus Syamsul; Wijaya, Harma Oktafia Lingga
Jurnal Sisfokom (Sistem Informasi dan Komputer) Vol 12, No 3 (2023): NOVEMBER
Publisher : ISB Atma Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32736/sisfokom.v12i3.1693

Abstract

The use of IoT devices has grown rapidly, leading to an increase in cyber attacks that pose greater security and privacy threats than ever before. One such threat is botnet attacks on IoT devices. An IoT botnet is a group of Internet-connected IoT devices infected with malware and remotely controlled by an attacker. Machine learning techniques can be employed to detect botnet attacks. The use of machine learning-based detection methods has been shown to be effective in identifying cyber attacks. The performance of the detection system in machine learning can be improved by utilizing data reduction methods. The data reduction process in classification is used to overcome the problem of scalability and computation resources in the IoT. This paper proposes a detection system using the Autoencoder reduction method and the Decision tree classification method. The test results demonstrate that the Deep Autoencoder algorithm can reduce data and memory usage from 1.62 GB to 75.9 MB, while also improving the performance of decision tree classification, resulting in a high level of accuracy up to 100%. The Autoencoder approach in conjunction with the Decision Tree exhibits superior capabilities compared to previous studies.
Deteksi Aktifitas Malware pada Internet of Things menggunakan Algoritma Decision Tree dan Random Forest Syamsul Arifin, M. Agus; Tri Susilo, Andri Anto; Susanto, Susanto; Martadinata, A. Taqwa; Santoso, Budi
KLIK: Kajian Ilmiah Informatika dan Komputer Vol. 4 No. 6 (2024): Juni 2024
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/klik.v4i6.1903

Abstract

The Internet of Things (IoT) has become an integral part of modern life, connecting smart devices to enhance efficiency and convenience. However, with the increased adoption of IoT, cybersecurity threats, particularly malware, have also risen. This research focuses on detecting malware attacks in IoT networks using machine learning algorithms, specifically Decision Tree and Random Forest. The dataset used is CICIoT2023, which includes various types of IoT network traffic such as BenignTraffic, Mirai-greeth_flood, Mirai-greip_flood, and Backdoor_Malware. In this study, both algorithms demonstrated exceptionally high accuracy on the training data, reaching 100%, and on the test data, achieving 99.94% accuracy for the Random Forest algorithm and 99.90% for the Decision Tree algorithm. Although the performance of both algorithms on the training data was almost identical, Random Forest showed better performance in detecting the Backdoor_Malware class compared to Decision Tree when using test data. Random Forest achieved a precision of 99%, recall of 64%, and F1-Score of 78%, while Decision Tree achieved a precision of 71%, recall of 72%, and F1-Score of 72%. Results from 10-fold cross-validation indicate that the models did not experience overfitting, suggesting reliable and well-generalized models. This research provides insights that the Random Forest algorithm is more effective in detecting malware attacks in IoT networks compared to Decision Tree, particularly in identifying the Backdoor_Malware class. These findings are expected to contribute to the development of more efficient and reliable malware detection systems for IoT networks.
IoT Security: Botnet Detection Using Self-Organizing Feature Map and Machine Learning Susanto; Stiawan, Deris; Santoso, Budi; Sidabutar, Alex Onesimus; Arifin, M. Agus Syamsul; Idris, Mohd Yazid; Budiarto, Rahmat
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 8 No 6 (2024): December 2024
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v8i6.5871

Abstract

The rapid advancement of Internet of Things (IoT) technology has created potential for progress in various aspects of life. However, the increasing number of IoT devices also raises the risk of cyberattacks, particularly IoT botnets often exploited by attackers. This is largely due to the limitations of IoT devices, such as constraints in capacity, power, and memory, necessitating an efficient detection system. This study aims to develop a resource-efficient botnet detection system by using the Self-Organizing Feature Map (SOFM) dimensionality reduction method in combination with machine learning algorithms. The proposed method includes a feature engineering process using SOFM to address high-dimensional data, followed by classification with various machine learning algorithms. The experiments evaluate performance based on accuracy, sensitivity, specificity, False Positive Rate (FPR), and False Negative Rate (FNR). Results show that the Decision Tree algorithm achieved the highest accuracy rate of 97.24%, with a sensitivity of 0.9523, specificity of 0.9932, and a fast execution time of 100.66 seconds. The use of SOFM successfully reduced memory consumption from 3.08 GB to 923MB. Experimental results indicate that this approach is effective for enhancing IoT security in resource-constrained devices.
Perbandingan Algoritma Decision tree dan Gradient Boosting pada Model Sistem Deteksi Serangan Siber di Jaringan Internet of Things Arifin, M. Agus Syamsul; Armanto, Armanto; Susanto, Susanto; Martadinata, A. Taqwa
InComTech : Jurnal Telekomunikasi dan Komputer Vol 15, No 1 (2025)
Publisher : Department of Electrical Engineering

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22441/incomtech.v15i1.26096

Abstract

Internet of things (IoT) memberikan banyak manfaat dimana membuat banyak perangkat pintar semakin dekat dan mudah digunakan. Penerapan teknologi IoT yang semakin luas memberikan banyak ancaman bari dalam segi keamanan data karena banyak perangkat yang terhubung dengan protocol yang beragam untuk mengatasinya dibutuhkan sebuah  Intrusion Detection System (IDS) yang handal untuk mendeteksi serangan dalam jaringan IoT. Dalam penelitian ini akan membangun sebuah model IDS menggunakan algoritma decision tree dan gradient boosting kemudian membandingkan performanya. Dataset yang digunakan pada penelitian ini menggunakan dataset dari CICIoT2023 karena kelas yang tidak seimbang dan ukuran dataset yang besar teknik Random Under Sampling (RUS) digunakan juga dalam penelitian ini. Hasil dari penelitian menunjukkan performa yang baik untuk setiap model IDS yang dibuat. Untuk data latih ketika tanpa menggunakan maupun teknik RUS algoritma decision tree mendapatkan akurasi tinggi mencapai 100% namun ketika menggunakan data uji gradient boosting mendapatkan hasil yang lebih baik yaitu 99,10% untuk sebelum penerapan teknik RUS dan 76,31% setelah penerapan teknik RUS.
Revolutionizing internet of things intrusion detection using machine learning with unidirectional, bidirectional, and packet features Elsi, Zulhipni Reno Saputra; Stiawan, Deris; Yudho Suprapto, Bhakti; Syamsul Arifin, M. Agus; Yazid Idris, Mohd.; Budiarto, Rahmat
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 14, No 4: August 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v14.i4.pp3047-3062

Abstract

Detection of attacks on internet of things (IoT) networks is an important challenge that requires effective and efficient solutions. This study proposes the use of various machine learning (ML) techniques in classifying attacks using unidirectional, bidirectional, and packet features. The proposed methods that implement decision tree (DT), random forest (RF), extreme gradient boosting classifier (XGBC), AdaBoost (AB) and linear discriminant analysis (LDA) work perfectly with all kinds of datasets and includes. It also works very well with data type-based feature selection (DTBFS) and correlation-based feature selection (CBFS). The experiment results show a significant improvement compared to previous studies and reveals that unidirectional and bidirectional features provide higher accuracy compared to packet features. Furthermore, ML models, particularly DT, and RF, have faster computing times compared to more complex deep learning models. This analysis also shows potential overfitting in some models, which requires further validation with different datasets. Based on these findings, we recommend the use of RF and DT for scenarios with unidirectional and bidirectional features, while AB and LDA for packet features. The study concludes that using the right ML techniques along with features that work in both directions can make an intrusion detection system for IoT networks becomes very accurate.
IoT Botnet Detection Using Autoencoders and Decision Trees Susanto, Susanto; Arifin, M. Agus Syamsul; Wijaya, Harma Oktafia Lingga
Jurnal Sisfokom (Sistem Informasi dan Komputer) Vol. 12 No. 3 (2023): NOVEMBER
Publisher : ISB Atma Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32736/sisfokom.v12i3.1693

Abstract

The use of IoT devices has grown rapidly, leading to an increase in cyber attacks that pose greater security and privacy threats than ever before. One such threat is botnet attacks on IoT devices. An IoT botnet is a group of Internet-connected IoT devices infected with malware and remotely controlled by an attacker. Machine learning techniques can be employed to detect botnet attacks. The use of machine learning-based detection methods has been shown to be effective in identifying cyber attacks. The performance of the detection system in machine learning can be improved by utilizing data reduction methods. The data reduction process in classification is used to overcome the problem of scalability and computation resources in the IoT. This paper proposes a detection system using the Autoencoder reduction method and the Decision tree classification method. The test results demonstrate that the Deep Autoencoder algorithm can reduce data and memory usage from 1.62 GB to 75.9 MB, while also improving the performance of decision tree classification, resulting in a high level of accuracy up to 100%. The Autoencoder approach in conjunction with the Decision Tree exhibits superior capabilities compared to previous studies.
MODEL MACHINE LEARNING TREE BASED UNTUK DETEKSI SERANGAN PADA SISTEM CHARGING ELECTRIC VEHICLE Novettralita, Ucky Pradestha; Amirulbahar, Azis; Ramadhany, Emha Diambang; Arifin, M. Agus Syamsul
Jurnal Teknologi Informasi Mura Vol 17 No 2 (2025): Jurnal Teknologi Informasi Mura DESEMBER
Publisher : LPPM UNIVERSITAS BINA INSAN

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32767/jti.v17i2.2755

Abstract

Cyberattack detection in Electric Vehicle Charging Infrastructure (EVCI) is increasingly critical as the global transition toward electric mobility accelerates to reduce carbon emissions. This study provides a comprehensive evaluation of machine learning models for cyberattack detection using the CICSEV2024 dataset. The performance of tree-based algorithms, including Decision Trees (DT), Random Forest (RF), and Gradient Boosting (GB), is compared to identify effective yet interpretable models. Experimental results demonstrate that these models achieve exceptional performance, with DT, RF, and GB reaching 100% accuracy and precision. Furthermore, 10-fold cross-validation on an imbalanced dataset (Benign class) confirms the models’ consistency, maintaining a score of 1.00 across all iterations. The proposed models also achieve a perfect Area Under the Curve (AUC) score of 1.00, indicating their robustness and reliability in detecting cyberattacks. The findings highlight that simple and interpretable tree-based models can achieve state-of-the-art performance in EVCI cybersecurity detection, offering practical implications for enhancing the security of electric vehicle charging infrastructures in real-world deployments.
MODEL MACHINE LEARNING TREE BASED UNTUK DETEKSI SERANGAN PADA SISTEM CHARGING ELECTRIC VEHICLE Novettralita, Ucky Pradestha; Amirulbahar, Azis; Ramadhany, Emha Diambang; Arifin, M. Agus Syamsul
Jurnal Teknologi Informasi Mura Vol 17 No 2 (2025): Jurnal Teknologi Informasi Mura DESEMBER
Publisher : LPPM UNIVERSITAS BINA INSAN

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32767/jti.v17i2.2755

Abstract

Cyberattack detection in Electric Vehicle Charging Infrastructure (EVCI) is increasingly critical as the global transition toward electric mobility accelerates to reduce carbon emissions. This study provides a comprehensive evaluation of machine learning models for cyberattack detection using the CICSEV2024 dataset. The performance of tree-based algorithms, including Decision Trees (DT), Random Forest (RF), and Gradient Boosting (GB), is compared to identify effective yet interpretable models. Experimental results demonstrate that these models achieve exceptional performance, with DT, RF, and GB reaching 100% accuracy and precision. Furthermore, 10-fold cross-validation on an imbalanced dataset (Benign class) confirms the models’ consistency, maintaining a score of 1.00 across all iterations. The proposed models also achieve a perfect Area Under the Curve (AUC) score of 1.00, indicating their robustness and reliability in detecting cyberattacks. The findings highlight that simple and interpretable tree-based models can achieve state-of-the-art performance in EVCI cybersecurity detection, offering practical implications for enhancing the security of electric vehicle charging infrastructures in real-world deployments.