Toward a deep learning-based intrusion detection system for IoT against botnet attacks

Idrissi, Idriss; Boukabous, Mohammed; Azizi, Mostafa; Moussaoui, Omar; Fadili, Hakim El

doi:10.11591/ijai.v10.i1.pp110-120

Cited by 62 publications

(42 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Chauhan and Atulkar [ 39 ] suggested the Light Gradient Boosting Machine (LGBM) model because it outperformed RF, Extra Tree (ET), Gradient Boost (GB) and XGBoost models. In [ 40 ], the Convolutional Neural Network (CNN) model outperformed the RNN, LSTM and GRU models. Huong et al [ 41 , 42 ] proposed a low-complexity edge-cloud DNN model, which achieved better performance than the kNN, DT, RF and SVM models.…”

Section: Review Of Related Workmentioning

confidence: 99%

SMOTE-DRNN: A Deep Learning Algorithm for Botnet Detection in the Internet-of-Things Networks

Popoola

Adebisi

Ande

et al. 2021

Sensors

View full text Add to dashboard Cite

Nowadays, hackers take illegal advantage of distributed resources in a network of computing devices (i.e., botnet) to launch cyberattacks against the Internet of Things (IoT). Recently, diverse Machine Learning (ML) and Deep Learning (DL) methods were proposed to detect botnet attacks in IoT networks. However, highly imbalanced network traffic data in the training set often degrade the classification performance of state-of-the-art ML and DL models, especially in classes with relatively few samples. In this paper, we propose an efficient DL-based botnet attack detection algorithm that can handle highly imbalanced network traffic data. Specifically, Synthetic Minority Oversampling Technique (SMOTE) generates additional minority samples to achieve class balance, while Deep Recurrent Neural Network (DRNN) learns hierarchical feature representations from the balanced network traffic data to perform discriminative classification. We develop DRNN and SMOTE-DRNN models with the Bot-IoT dataset, and the simulation results show that high-class imbalance in the training data adversely affects the precision, recall, F1 score, area under the receiver operating characteristic curve (AUC), geometric mean (GM) and Matthews correlation coefficient (MCC) of the DRNN model. On the other hand, the SMOTE-DRNN model achieved better classification performance with 99.50% precision, 99.75% recall, 99.62% F1 score, 99.87% AUC, 99.74% GM and 99.62% MCC. Additionally, the SMOTE-DRNN model outperformed state-of-the-art ML and DL models.

show abstract

Section: Review Of Related Workmentioning

confidence: 99%

SMOTE-DRNN: A Deep Learning Algorithm for Botnet Detection in the Internet-of-Things Networks

Popoola

Adebisi

Ande

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Where k represents the subset of the original dataset (K) that optimizes f1 and f2 (the objectives). The second part involves the evaluation of the selected feature subsets based on accuracy (an established performance evaluation metric), as provided in (3). Accuracy calculation requires the division of the instances that are classified correctly by all instances.…”

Section: 𝑓1 = |𝑘|mentioning

confidence: 99%

Optimized machine learning algorithm for intrusion detection

Alhayali

Aljanabi

Ali

et al. 2021

IJEECS

View full text Add to dashboard Cite

Intrusion detection is mainly achieved by using optimization algorithms. The need for optimization algorithms for intrusion detection is necessitated by the increasing number of features in audit data, as well as the performance failure of the human-based smart intrusion detection system (IDS) in terms of their prolonged training time and classification accuracy. This article presents an improved intrusion detection technique for binary classification. The proposal is a combination of different optimizers, including Rao optimization algorithm, extreme learning machine (ELM), support vector machine (SVM), and logistic regression (LR) (for feature selection & weighting), as well as a hybrid Rao-SVM algorithm with supervised machine learning (ML) techniques for feature subset selection (FSS). The process of selecting the least number of features without sacrificing the FSS accuracy was considered a multi-objective optimization problem. The algorithm-specific, parameter-less concept of the proposed Rao-SVM was also explored in this study. The KDDCup 99 and CICIDS 2017 were used as the intrusion dataset for the experiments, where significant improvements were noted with the new Rao-SVM compared to the other algorithms. Rao-SVM presented better results than many existing works by reaching 100% accuracy for KDDCup 99 dataset and 97% for CICIDS dataset.

show abstract

“…Deep learning models necessitates a lot of data and time while training [17], [18]. Transfer learning is a technique that benefits from an already trained weight on big datasets for a long period of time and transfer this knowledge [19] to the targeted model.…”

Section: Transfer Learningmentioning

confidence: 99%

A comparative study of deep learning based language representation learning models

Boukabous¹,

Azizi²

2021

IJEECS

Self Cite

View full text Add to dashboard Cite

Deep learning (DL) approaches use various processing layers to learn hierarchical representations of data. Recently, many methods and designs of natural language processing (NLP) models have shown significant development, especially in text mining and analysis. For learning vector-space representations of text, there are famous models like Word2vec, GloVe, and fastText. In fact, NLP took a big step forward when BERT and recently GTP-3 came out. In this paper, we highlight the most important language representation learning models in NLP and provide an insight of their evolution. We also summarize, compare and contrast these different models on sentiment analysis, and thus discuss their main strengths and limitations. Our obtained results show that BERT is the best language representation learning model.

show abstract

Toward a deep learning-based intrusion detection system for IoT against botnet attacks

Cited by 62 publications

References 21 publications

SMOTE-DRNN: A Deep Learning Algorithm for Botnet Detection in the Internet-of-Things Networks

SMOTE-DRNN: A Deep Learning Algorithm for Botnet Detection in the Internet-of-Things Networks

Optimized machine learning algorithm for intrusion detection

A comparative study of deep learning based language representation learning models

Contact Info

Product

Resources

About