Deep Learning in Intrusion Detection Systems

• Published in: 2018 International Congress on Big Data, Deep Learning and Fighting Cyber Terrorism (IBIGDELFT) pp. 113 - 116
• Main Authors: Karatas, Gozde, Demir, Onder, Koray Sahingoz, Ozgur
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.12.2018
• Subjects: Big Data; Deep learning; Feature extraction; Intrusion detection; Machine learning algorithms; Security
• DOI: 10.1109/IBIGDELFT.2018.8625278

In recent years, due to the emergence of boundless communication paradigm and increased number of networked digital devices, there is a growing concern about cybersecurity which tries to preserve either the information or the communication technology of the system. Intruders discover new attack types day by day, therefore to prevent these attacks firstly they need to be identified correctly by the used intrusion detection systems (IDSs), and then proper responses should be given. IDSs, which play a very crucial role for the security of the network, consist of three main components: data collection, feature selection/conversion and decision engine. The last component directly affects the efficiency of the system and use of machine learning techniques is one of most promising research areas. Recently, deep learning has been emerged as a new approach which enables the use of Big Data with a low training time and high accuracy rate with its distinctive learning mechanism. Consequently, it has been started to use in IDS systems. In this paper, it is aimed to survey deep learning based intrusion detection system approach by making a comparative work of the literature and by giving the background knowledge either in deep learning algorithms or in intrusion detection systems.