Project Title: Intrusion Detection using CNN
Overview: This project implements an intrusion detection system using Convolutional Neural Networks (CNNs) to analyze network traffic. The model is trained on the Simargyl_2022 dataset, which contains labeled instances of normal and malicious network activity. The implementation is done in Google Colab, providing a convenient platform for collaborative development and execution.
Dataset: The dataset used in this project is sourced from Kaggle. To access the dataset, please follow these steps: Go to the Kaggle website and download the dataset titled simargyl_2022 from https://www.kaggle.com/datasets/h2020simargl/simargl2022. Upload the downloaded dataset zip file to your Google Colab environment. Extract the dataset zip file using the provided code snippet in the Colab notebook.
Instructions: Open the provided Google Colab notebook in your browser. Follow the instructions provided in the notebook to set up the environment, upload and extract the dataset, and train the CNN model. Execute the code cells sequentially to train the model on the dataset. Monitor the training progress and adjust hyperparameters if necessary. After training, evaluate the model's performance using the provided evaluation metrics. This will give you insights into the model's effectiveness in classifying network traffic. Optionally, you can experiment with different architectures, optimization techniques, or preprocessing methods to further improve the model's performance.
Results: The notebook will display the training and evaluation results, including metrics such as accuracy, precision, recall, and F1-score. These metrics will help assess the effectiveness of the intrusion detection system in classifying network traffic.
Contributors: Thota Sai Harshitha
Acknowledgments: We would like to acknowledge Kaggle for providing the dataset used in this project. Additionally, we appreciate the support of the Google Colab platform for facilitating collaborative development and execution of machine learning projects.
References: [1] G. Muhammad, M. S. Hossain and S. Garg, "Stacked Autoencoder-Based Intrusion Detection System to Combat Financial Fraudulent," in IEEE Internet of Things Journal, vol. 10, no. 3, pp. 2071-2078, 1 Feb.1, 2023, doi: 10.1109/JIOT.2020.3041184. [2] NARAYANA, Y. V., & SREEDEVI, M. (2023). Deep Neural System for Identifying Cybercrime Activities in Networks. Journal of Theoretical and Applied Information Technology, 101(16). [3] F. Aloul, I. Zualkernan, N. Abdalgawad, L. Hussain and D. Sakhnini, "Network Intrusion Detection on the IoT Edge Using Adversarial Autoencoders," 2021 International Conference on Information Technology (ICIT), Amman, Jordan, 2021, pp. 120-125, doi: 10.1109/ICIT52682.2021.9491694 [4] F. Kamalov, R. Zgheib, H. H. Leung, A. Al-Gindy and S. Moussa, "Autoencoder-based Intrusion Detection System," 2021 International Conference on Engineering and Emerging Technologies (ICEET), Istanbul, Turkey, 2021, pp. 1-5, doi: 10.1109/ICEET53442.2021.9659562. [5] R. Zhao et al., "An Efficient Intrusion Detection Method Based on Dynamic Autoencoder," in IEEE Wireless Communications Letters, vol. 10, no. 8, pp. 1707-1711, Aug. 2021, doi: 10.1109/LWC.2021.3077946.