Developing new deep-learning model to enhance network intrusion classification

Azzaoui, Hanane; Boukhamla, Akram Zine Eddine; Arroyo, David; Bensayah, Abdallah

doi:10.1007/s12530-020-09364-z

Cited by 31 publications

(23 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…depicts that the proposed SVM-ANN-IDS offer with existing Azzaoui et al, 21 Sah et al, 22 Ravi et al, 23 Kasongo, 24 Halbouni et al, 25 21 Sah et al, 22 Ravi et al, 23 Kasongo, 24 Halbouni et al, 25 21 Sah et al, 22 Ravi et al, 23 Kasongo, 24 Halbouni et al, 25 Dhanya et al, 26 and GSR et al, 27 methods. The SVM-ANN-IDS model provide 24.38%, 15.26%, 23.07%, 14.26%, 12.45%, 22.96% and 24.10% greater recall compared with existing Azzaoui et al, 21 Sah et al, 22 Ravi et al, 23 Kasongo, 24 Halbouni et al, 25 Dhanya et al, 26 and GSR et al, 27 21 Sah et al, 22 Ravi et al, 23 Kasongo, 24 Halbouni et al, 25 and GSR et al, 27 21 Sah et al, 22 Ravi et al, 23 Kasongo, 24 Halbouni et al, 25 and Dhanya et al, 26 methods. The proposed SVM-ANN-IDS provide 14.36%, 27.36%, 32.93%, 24.28%, 20.27%, and 21.48% lesser error rate compared with existing Azzaoui et al, 21 Sah et al, 22 Ravi et al, 23 21 Sah et al, 22 Ravi et al, 23 Kasongo, 24 Halbouni et al,…”

Section: Justification Of Studymentioning

confidence: 79%

“…The effectiveness of the proposed method is assessed using performance metrics. Then the SVM-ANN-IDS method is analyzed with existing DNN-IDS, 21 RNN-SVM-IDS 22 and RNN-IDS 23 methods. Table 3 shows simulation parameters settings.…”

Section: Resultsmentioning

confidence: 99%

“…Several researches have been presented related to intrusion identification scheme for maximizing network safety with the machine learning; some of the recent researches are revised below. Azzaoui et al, 21 have introduced a novel deep-learning model to improve the network intrusion categorization. In the presented study, a novel deep neural network (DNN)-based intrusion detection system (IDS) technique for network traffic categorization was presented.…”

Section: Literature Reviewmentioning

confidence: 99%

“…• Then the effectiveness of the proposed technique is examined with performance parameters using the CICIDS2017 and the SVM-ANN-IDS approaches are compared to the existing DNN-IDS, 21 RNN-SVM-IDS 22 and RNN-IDS 23 models.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Intrusion detection system based on the beetle swarm optimization and K‐RMS clustering algorithm

Pran,

Raja,

Jeyasudha

2024

Adaptive Control & Signal

View full text Add to dashboard Cite

SummaryIntrusion detection is a cyber‐security method that is significant for network security. It is utilized to detect behaviors that compromise security and privacy within a network or in the context of a computer system. To enhance the identification, an Intrusion Detection System Based on the Beetle Swarm Optimization and K‐RMS Clustering Algorithm cluster‐based hybrid classifiers is proposed in this manuscript. Here, the data is amassed from CICIDS2017 dataset. Then the data is preprocessed to eradicate the unwanted noise. After completing the preprocessed data, it can be clustered by using K‐RMS clustering algorithm. This algorithm cluster the entire data to the associated cluster set depending on the data behavior. The classification algorithm is considered to predict the data as normal or attacking behaviors. The hybrid classification is used to predict the data. The solitary predictor aims to achieve high detection rates and accuracy. The hybrid classifiers, such as support vector machines, artificial neural networks are applied to recognize the normal or intruder. The performance of the SVM‐ANN‐IDS method attains 22.05%, 15.87%, 27.25% higher accuracy, 23.90% and 28.53% higher precision, 29.29%, 19.19% and 23.27% higher specificity and 18.28%, 24.36% and 27.49% greater recall when compared to the existing models, like developing novel deep‐learning model to improve network intrusion categorization (DNN‐IDS), Intrusion identification scheme on real‐time data traffic under machine learning techniques along feature selection method (RNN‐SVM‐IDS) and recurrent deep learning basis feature fusion ensemble meta‐classifier for intellectual network intrusion identification scheme (RNN‐IDS) respectively.

show abstract

Section: Justification Of Studymentioning

confidence: 79%

Section: Resultsmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Intrusion detection system based on the beetle swarm optimization and K‐RMS clustering algorithm

Pran,

Raja,

Jeyasudha

2024

Adaptive Control & Signal

View full text Add to dashboard Cite

show abstract

“…The results showed that the proposed method achieved improved performance compared to the current state‐of‐the‐art systems. Reference 25 proposed a new deep‐learning model for network intrusion detection using deep neural networks. The performance of the proposed method was evaluated on NSLKDD and CICIDS2017 datasets.…”

Section: Introductionmentioning

confidence: 99%

AWC‐NIDS: Attack‐wise customized network intrusion detection system using machine learning, concurrency, and distributed systems

Guney¹

2023

Concurrency and Computation

View full text Add to dashboard Cite

SummaryWith digitization and modern network applications, information security has gained a tremendous importance. Therefore, accurate and efficient detection systems are crucial for maintaining proactive security in computer networks. Machine learning (ML) has shown great potential as a promising solution since it can teach a machine to distinguish malicious and normal network activities. However, recently proposed methods are suffering from at least one of the following: detection accuracy, false alarm rate, and computational complexity issues. The main reason behind this problem is the complexity of the model in terms of attack types. From the ML perspective, intrusion detection is a classification problem where each attack type is identified by a set of different features, and features are used for classifying network activities. Thus, training an ML algorithm to detect more than one attack type leads to a more complex model; the increasing number of used features contributes positively to the model complexity, and may result in relatively lower detection accuracy or a higher false positive rate. To tackle this problem, this study proposes an attack‐wise customized network intrusion detection system (AWC‐NIDS) based on ML, concurrency, and distributed systems to achieve accurate and efficient network‐wide intrusion detection. Since CICIDS2017 contains many modern attacks, it was used for model development and performance evaluation. The experimental results showed that the proposed methodology achieved high classification performance for all datasets with a small number of features. However, it was observed that the lowest accuracy was achieved for the comprehensive dataset (which contains all attack types); for the single attack‐type datasets, the obtained accuracy was above 99%. This finding proves the concept of attack‐wise customization for intrusion detection and shows the significance of the proposed methodology. In conclusion, this framework is promising for implementing robust and accurate cybersecurity systems for traditional and modern networking.

show abstract