

Siamese Neural Network-Based Intrusion Detection System
Abstract
Intrusion Detection Systems (IDS) play a critical role in cybersecurity, identifying and mitigating unauthorized access. Traditional IDS face challenges related to high false-positive rates and computational costs. In this paper, we propose a novel approach using a Siamese Neural Network (SNN) to improve detection accuracy while optimizing resource utilization. Our model is evaluated on the UNSW-NB15 dataset, demonstrating superior performance compared to conventional IDS solutions. This study provides an in-depth discussion on the methodology, dataset preparation, model architecture, hyperparameter tuning, feature extraction, evaluation metrics, and comparative analysis.
References
Hindy, Hanan, Christos Tachtatzis, Robert Atkinson, Ethan Bayne, and Xavier Bellekens. "Developing a siamese network for intrusion detection systems." In Proceedings of the 1st Workshop on Machine Learning and Systems, pp. 120-126. 2021.
Pawlicki, Marek, Rafał Kozik, and Michał Choraś. "Improving siamese neural networks with border extraction sampling for the use in real-time network intrusion detection." In 2023 International Joint Conference on Neural Networks (IJCNN), pp. 1-8. IEEE, 2023.
Hindy, Hanan, Christos Tachtatzis, Robert Atkinson, David Brosset, Miroslav Bures, Ivan Andonovic, Craig Michie, and Xavier Bellekens. "Leveraging siamese networks for one-shot intrusion detection model." Journal of Intelligent Information Systems 60, no. 2 (2023): 407-436.
Nguyen, Dinh Hoang, Nam Khanh Tran, and Nhien-An Le-Khac. "A Siamese-Based Approach for Network Intrusion Detection Systems in Software-Defined Networks." In International Conference on Future Data and Security Engineering, pp. 199-211. Singapore: Springer Nature Singapore, 2023.
Park, Daekyeong, Sangsoo Kim, Hyukjin Kwon, Dongil Shin, and Dongkyoo Shin. "Host-based intrusion detection model using siamese network." IEEE Access 9 (2021):
-76623.
Moustakidis, Serafeim, and Patrik Karlsson. "A novel feature extraction methodology using Siamese convolutional neural networks for intrusion detection." Cybersecurity 3, no. 1 (2020): 16.
Bedi, Punam, Neha Gupta, and Vinita Jindal. "Siam-IDS: Handling class imbalance problem in intrusion detection systems using siamese neural network." Procedia Computer Science 171 (2020): 780-789.
Bedi, Punam, Neha Gupta, and Vinita Jindal. "I-SiamIDS: an improved
Siam-IDS for handling class imbalance in network-based intrusion detection systems." Applied Intelligence 51, no. 2(2021): 1133-1151.
Hindy, Hanan, Christos Tachtatzis, Robert Atkinson, David Brosset, Miroslav Bures, Ivan Andonovic, Craig Michie, and Xavier Bellekens. "Leveraging siamese networks for one-shot intrusion detection model." Journal of Intelligent Information Systems 60, no. 2 (2023): 407-436.
Moustakidis, Serafeim, and Patrik Karlsson. "A novel feature extraction methodology using Siamese convolutional neural networks for intrusion detection." Cybersecurity 3, no. 1 (2020): 16.
Refbacks
- There are currently no refbacks.