Experiments with using a Convolutional Neural Network to detect intrusion based on network traffic features. Targeted intrusion classes are:
'DDoS', 'PortScan', 'Bot', 'Infiltration','WebAttack - BruteForce', 'WebAttack - XSS', 'WebAttack - SqlInjection','FTP-Patator', 'SSH-Patator', 'DoSslowloris', 'DoSSlowhttptest','DoSHulk', 'DoSGoldenEye', 'Heartbleed'
CICIDS2017 Dataset: Iman Sharafaldin, Arash Habibi Lashkari, and Ali A. Ghorbani, “Toward Generating a New Intrusion Detection Dataset and Intrusion Traffic Characterization”, 4th International Conference on Information Systems Security and Privacy (ICISSP), Portugal, January 2018
Based on: Jan Lansky, Saqib Ali, Mokhtar Mohammadi, Mohammed Kamal Majeed, Sarkhel H. Taher Karim, Shima Rashidi, Mehdi Hosseinzadeh, Amir Masoud Rahmani, "Deep Learning-Based Intrusion Detection Systems: A Systematic Review", Access IEEE, vol. 9, pp. 101574-101599, 2021.