ავტორი: Seiba Alhassan, Gaddafi Abdul-Salaam, Yaw Missah
ორგანიზაცია: Kwame Nkrumah University of Science and Technology, Dr Hilla Limann Technical University


საკვანძო სიტყვები: Autoencoder, IDS, encoder, decoder, bottleneck
აბსტრაქტი. Sensitive data processed, stored, and transmitted on a computer requires a mechanism to protect it from unauthorized access. Several techniques have been proposed, including Intrusion Detection Systems (IDS), to protect computer networks from attacks. Autoencoders, a deep learning technique, have been explored by several researchers aiming to improve the performance of existing IDS. Despite the significant improvements seen with the use of autoencoders, the issues of low detection accuracy and high false alarm rates continue to be major problem. The architecture of a deep autoencoder, including the number of layers, neurons, and the bottleneck, affects its performance. This study is conducted to determine the optimal bottleneck size based on the architecture of a two-layer autoencoder. The study utilizes the benchmark dataset NSL-KDD to train, test, and validate the model. The experimental results from our proposed system reveal that the optimal bottleneck size for an autoencoder is obtained by setting it to 60% of the size of the previous hidden layer.


Alam, Naushad, and Muqeem Ahmed. 2023. “Zero-Day Network Intrusion Detection Using Machine Learning Approach,” no. April: 194–201.
Almaiah, Mohammed Amin, Omar Almomani, Adeeb Alsaaidah, Shaha Al-otaibi, Nabeel Bani-hani, Ahmad K Al Hwaitat, Ali Al-zahrani, Abdalwali Lutfi, Ali Bani Awad, and Theyazn H H Aldhyani. 2022. “Machine Kernels.”
Das, Abhijit. 2022. “An Efficient Feature Selection Approach for Intrusion Detection System Using Decision Tree” 13 (2).
Garg, Deepak, N. V. Narendra Kumar, and Rudrapatna Shyamasundar. n.d. “Information Systems Security : 15th International Conference, ICISS 2019, Hyderabad, India, December 16-20, 2019, Proceedings,” 345. Accessed February 7, 2022. https://www.kobo.com/us/en/ebook/information-systems-security-4.
Haripriya, C, and M P Prabhudev Jagadeesh. 2022. “An Efficient Autoencoder-Based Deep Learning Technique to Detect Network Intrusions” 13 (7): 1–10. https://doi.org/10.14456/ITJEMAST.2022.142.
Hendi, Alva, Ike Verawati, and Richki Hardi. 2022. “An Intrusion Detection System Using SDAE to Enhance Dimensional Reduction in Machine Learning” 6 (June): 306–16.
Kasongo, Sydney Mambwe. 2023. “A Deep Learning Technique for Intrusion Detection System Using a Recurrent Neural Networks Based Framework.” Computer Communications 199 (October 2022): 113–25. https://doi.org/10.1016/j.comcom.2022.12.010.
Li, Yue, Ang Li, Anxing Wen, and Xian Xie. 2022. “Research on Intrusion Detection Based on Neural Network Optimized by Genetic Algorithm” en: 8–11.
Logeswari, G, S Bose, and T Anitha. 2023. “An Intrusion Detection System for SDN Using Machine Learning.” https://doi.org/10.32604/iasc.2023.026769.
Makarand, L. 2022. “Machine Learning Applications in Engineering Education and Management Intrusion Detection System Attack Detection and Classification Model with Feed-Forward LSTM Gate in Conventional Dataset” 02 (01): 20–29.
Mirsky, Yisroel, Tomer Doitshman, Yuval Elovici, and Asaf Shabtai. 2018. “Kitsune : An Ensemble of Autoencoders for Online Network Intrusion Detection,” no. February: 18–21.
Pranto, Badiuzzaman, Hasibul Alam Ratul, Mahidur Rahman, and Ishrat Jahan Diya. 2022. “Performance of Machine Learning Techniques in Anomaly Detection with Basic Feature Selection Strategy - A Network Intrusion Detection System” 13 (1). https://doi.org/10.12720/jait.13.1.36-44.
Ramasamy, Mathiyalagan, and Pamela Vinitha Eric. 2023. “A Tree Growth Based Forward Feature Selection Algorithm for Intrusion Detection System on Convolutional Neural Network” 12 (1): 472–82. https://doi.org/10.11591/eei.v12i1.4015.
abir, Maha, Jawad Ahmad, and Daniyal Alghazzawi. 2023. “A Lightweight Deep Autoencoder Scheme for Cyberattack Detection in the Internet of Things.” https://doi.org/10.32604/csse.2023.034277.
Schmidt, Mark. 2020. “TheRepository at St . Cloud State Autoencoder-Based Representation Learning to Predict Anomalies in Computer Networks.”
Shahid, Mustafizur R., Gregory Blanc, Zonghua Zhang, and Herve Debar. 2019. “Anomalous Communications Detection in IoT Networks Using Sparse Autoencoders.” 2019 IEEE 18th International Symposium on Network Computing and Applications, NCA 2019, 1–5.
Shone, Nathan, Tran Nguyen Ngoc, Vu Dinh Phai, and Qi Shi. 2018. “A Deep Learning Approach to Network Intrusion Detection.” IEEE Transactions on Emerging Topics in Computational Intelligence 2 (1): 41–50. https://doi.org/10.1109/TETCI.2017.2772792.
Shone, Nathan, Tran Nguyen Ngoc, Vu Dinh Phai, and Qi Shi. 2018. “A Deep Learning Approach to Network Intrusion Detection.” IEEE Transactions on Emerging Topics in Computational Intelligence 2 (1): 41–50. https://doi.org/10.1109/TETCI.2017.2772792.
Siddique, Kamran, Zahid Akhtar, Farrukh Aslam Khan, and Yangwoo Kim. 2019. “KDD Cup 99 Data Sets: A Perspective on the Role of Data Sets in Network Intrusion Detection Research.” Computer 52 (2): 41–51. https://doi.org/10.1109/MC.2018.2888764.
Sindian, Samar, and Samer Sindian. 2020. “An Enhanced Deep Autoencoder-Based Approach for DDoS Attack Detection 3 Deep Neural Network 2 Related Work” 15: 716–24. https://doi.org/10.37394/23203.2020.15.72.
Song, Tianbao, Jingbo Sun, B O Chen, Weiming Peng, and Jihua Song. 2019. “Latent Space Expanded Variational Autoencoder for Sentence Generation.” IEEE Access 7: 144618–27. https://doi.org/10.1109/ACCESS.2019.2944630.
Song, Youngrok, Sangwon Hyun, and Yun Gyung Cheong. 2021. “Analysis of Autoencoders for Network Intrusion Detection†.” Sensors 21 (13): 1–23. https://doi.org/10.3390/s21134294.
Wang, Chao, Hongri Liu, Yunxiao Sun, Yuliang Wei, Kai Wang, and Bailing Wang. 2022. “Dimension Reduction Technique Based on Supervised Autoencoder for Intrusion Detection of Industrial Control Systems” 2022.
Xu, W E N, Julian Jang-jaccard, Amardeep Singh, and Fariza Sabrina. 2021. “Improving Performance of Autoencoder-Based Network Anomaly Detection on NSL-KDD Dataset.” IEEE Access 9: 140136–46. https://doi.org/10.1109/ACCESS.2021.3116612.
Yu, Yang, Jun Long, and Zhiping Cai. 2017. “Network Intrusion Detection through Stacking Dilated Convolutional Autoencoders.” Security and Communication Networks 2017. https://doi.org/10.1155/2017/4184196.
Zhang, Baoan, Yanhua Yu, and Jie Li. 2018. “Network Intrusion Detection Based on Stacked Sparse Autoencoder and Binary Tree Ensemble Method.” 2018 IEEE International Conference on Communications Workshops, ICC Workshops 2018 - Proceedings, no. 61702046: 1–6. https://doi.org/10.1109/ICCW.2018.8403759.