I want to make an IDS or IPS (or combination of both: IDPS) system based on deep learning method like CNN. please guide me if you have any information on it.
Deep learning has a variety of methods according to the problem. I recommend starting with MLP and later testing alternatives like CNN or hybrid models.
Park, S. T., Li, G., & Hong, J. C. (2018). A study on smart factory-based ambient intelligence context-aware intrusion detection system using machine learning. Journal of Ambient Intelligence and Humanized Computing, 1-8.
Aljawarneh, S., Aldwairi, M., & Yassein, M. B. (2018). Anomaly-based intrusion detection system through feature selection analysis and building hybrid efficient model. Journal of Computational Science, 25, 152-160.
Lee, B., Amaresh, S., Green, C., & Engels, D. (2018). Comparative Study of Deep Learning Models for Network Intrusion Detection. SMU Data Science Review, 1(1), 8.
Mighan, S. N., & Kahani, M. (2018, May). Deep Learning Based Latent Feature Extraction for Intrusion Detection. In Electrical Engineering (ICEE), Iranian Conference on (pp. 1511-1516). IEEE.
Yes, DNN is one stop solution to every problem. For intrusion detection you can try CNN, GRU or LSTM. But literature suggest that RNNs perform well and robust in ID systems.
Regards
Suheel
- Badges
- Science topic