Comparative Study of BiGRU with Multi-Head Attention and CNN for Network Intrusion Detection Using a Cleaned and Balanced CSE-CIC-IDS 2018 Dataset

Suresh Kumar Balasubramanian; Senthilkumar Perumal

Makale detayları

Comparative Study of BiGRU with Multi-Head Attention and CNN for Network Intrusion Detection Using a Cleaned and Balanced CSE-CIC-IDS 2018 Dataset

Yazarlar:

Suresh Kumar Balasubramanian | Senthilkumar Perumal

Yayıncı:

Murat YAKAR

Ana Başlıklar:

Computer System Software

Dergi:

Turkish Journal of Engineering Vol.9 Issue 4, pp.725-737

Belge Tipi:

Makale

Yayın Tarihi:

8/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001360057

pISSN:

2587-1366

Anahtar kelimeler:

Özet:

 With the age of advanced cyber attacks, robust intrusion detection systems are inevitable in order to protect the network from insecurity. This work presents a new comparative performance evaluation of two deep learning models, namely, Bidirectional Gated Recurrent Unit with Multi Head Attention BiGRU  MHA and Convolutional Neural Network CNN, on the updated CSE-CIC-IDS 2018 dataset Version 1, 2024. The data set was cleaned and balanced meticulously by eliminating duplicate entries and a two-stage resampling method with random undersampling accompanied with synthetic minority oversampling for accurate representation of both frequent as well as infrequent types of attacks. The experimental results confirm that both models provided superior detection performance, with BiGRU  MHA consistently outperforming CNN. Specifically, BiGRU  MHA provided 99.65 percent accuracy as well as ROC AUC of 99.71 percent, whereas CNN provided 98.85 percent accuracy as well as ROC AUC of 98.92 percent. The observations identify the advantage of using the combination of temporal sequence modeling as well as attention for identifying advanced intrusion patterns in network traffic. Generally, the results confirm that the use of deep temporal learning in combination with structured preparation of the data holds the capability for leading to highly effective intrusion detection, with great potential for strengthening cybersecurity solutions.

 With the age of advanced cyber attacks, robust intrusion detection systems are inevitable in order to protect the network from insecurity. This work presents a new comparative performance evaluation of two deep learning models, namely, Bidirectional Gated Recurrent Unit with Multi Head Attention BiGRU  MHA and Convolutional Neural Network CNN, on the updated CSE-CIC-IDS 2018 dataset Version 1, 2024. The data set was cleaned and balanced meticulously by eliminating duplicate entries and a two-stage resampling method with random undersampling accompanied with synthetic minority oversampling for accurate representation of both frequent as well as infrequent types of attacks. The experimental results confirm that both models provided superior detection performance, with BiGRU  MHA consistently outperforming CNN. Specifically, BiGRU  MHA provided 99.65 percent accuracy as well as ROC AUC of 99.71 percent, whereas CNN provided 98.85 percent accuracy as well as ROC AUC of 98.92 percent. The observations identify the advantage of using the combination of temporal sequence modeling as well as attention for identifying advanced intrusion patterns in network traffic. Generally, the results confirm that the use of deep temporal learning in combination with structured preparation of the data holds the capability for leading to highly effective intrusion detection, with great potential for strengthening cybersecurity solutions.

 With the age of advanced cyber attacks, robust intrusion detection systems are inevitable in order to protect the network from insecurity. This work presents a new comparative performance evaluation of two deep learning models, namely, Bidirectional Gated Recurrent Unit with Multi Head Attention BiGRU  MHA and Convolutional Neural Network CNN, on the updated CSE-CIC-IDS 2018 dataset Version 1, 2024. The data set was cleaned and balanced meticulously by eliminating duplicate entries and a two-stage resampling method with random undersampling accompanied with synthetic minority oversampling for accurate representation of both frequent as well as infrequent types of attacks. The experimental results confirm that both models provided superior detection performance, with BiGRU  MHA consistently outperforming CNN. Specifically, BiGRU  MHA provided 99.65 percent accuracy as well as ROC AUC of 99.71 percent, whereas CNN provided 98.85 percent accuracy as well as ROC AUC of 98.92 percent. The observations identify the advantage of using the combination of temporal sequence modeling as well as attention for identifying advanced intrusion patterns in network traffic. Generally, the results confirm that the use of deep temporal learning in combination with structured preparation of the data holds the capability for leading to highly effective intrusion detection, with great potential for strengthening cybersecurity solutions.

 With the age of advanced cyber attacks, robust intrusion detection systems are inevitable in order to protect the network from insecurity. This work presents a new comparative performance evaluation of two deep learning models, namely, Bidirectional Gated Recurrent Unit with Multi Head Attention BiGRU  MHA and Convolutional Neural Network CNN, on the updated CSE-CIC-IDS 2018 dataset Version 1, 2024. The data set was cleaned and balanced meticulously by eliminating duplicate entries and a two-stage resampling method with random undersampling accompanied with synthetic minority oversampling for accurate representation of both frequent as well as infrequent types of attacks. The experimental results confirm that both models provided superior detection performance, with BiGRU  MHA consistently outperforming CNN. Specifically, BiGRU  MHA provided 99.65 percent accuracy as well as ROC AUC of 99.71 percent, whereas CNN provided 98.85 percent accuracy as well as ROC AUC of 98.92 percent. The observations identify the advantage of using the combination of temporal sequence modeling as well as attention for identifying advanced intrusion patterns in network traffic. Generally, the results confirm that the use of deep temporal learning in combination with structured preparation of the data holds the capability for leading to highly effective intrusion detection, with great potential for strengthening cybersecurity solutions.

Makale detayları

Comparative Study of BiGRU with Multi-Head Attention and CNN for Network Intrusion Detection Using a Cleaned and Balanced CSE-CIC-IDS 2018 Dataset

Yazarlar:

Suresh Kumar Balasubramanian | Senthilkumar Perumal

Yayıncı:

Murat YAKAR

Ana Başlıklar:

Computer System Software

Dergi:

Turkish Journal of Engineering Vol.9 Issue 4, pp.725-737

Belge Tipi:

Makale

Yayın Tarihi:

8/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001360057

pISSN:

2587-1366

Network Intrusion Detection

Deep Learning

BiGRU with Attention

Convolutional Neural Networks (CNN)

CSE-CIC-IDS2018 Dataset

Cybersecurity

Sayı

Makale detayları

Comparative Study of BiGRU with Multi-Head Attention and CNN for Network Intrusion Detection Using a Cleaned and Balanced CSE-CIC-IDS 2018 Dataset

Yazarlar: Suresh Kumar Balasubramanian | Senthilkumar Perumal

Yayıncı: Murat YAKAR

Ana Başlıklar: Computer System Software

Dergi: Turkish Journal of Engineering Vol.9 Issue 4, pp.725-737

Belge Tipi: Makale

Yayın Tarihi: 8/2025

Belge Dili: İngilizce

Document ID (Org No.): 2001360057

pISSN: 2587-1366

Network Intrusion Detection

Deep Learning

BiGRU with Attention

Convolutional Neural Networks (CNN)

CSE-CIC-IDS2018 Dataset

Cybersecurity

Sayı

Yazarlar:

Suresh Kumar Balasubramanian | Senthilkumar Perumal

Yayıncı:

Murat YAKAR

Ana Başlıklar:

Computer System Software

Dergi:

Turkish Journal of Engineering Vol.9 Issue 4, pp.725-737

Belge Tipi:

Makale

Yayın Tarihi:

8/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001360057

pISSN:

2587-1366