| Intrusion Detection in Distributed Bigdata Systems |
| Paper ID : 1094-ISCBAS |
| Authors |
|
Bashar Ibrahim Hameed *1, Kamal El-Dahshan2, Abdallah adel Alhabashy3 1Iraqi Sunni Affairs, Iraq 2Professor in Computer science 3Al-Azhar university |
| Abstract |
| Intrusion Detection System (IDS) is a software application that monitors network or system-related activities. It checks whether it has any ongoing malicious activities or viruses that attack them. The IDS has had a challenging problem for many years as unknown attacks have taken place even after various approaches have been proposed to design the IDS so that it could work efficiently. Many attacks/threats/malicious activities remain undetected even after proper measures and secured configurations are taken. The critical part is that organizations suffer from security flaws, and inappropriate configuration of firewalls leads to data breaches. Usually, IDSs are deployed with other preventive security mechanisms, like authentication and authorization. IDSs act as the second line of defense to protect the information systems. However, many reasons can make intrusion detection necessary for a defense system. For instance, numerous classical and traditional applications were developed and expanded without considering security during the design and implementation phases. Both systems and applications were created to work within diverse environments, making them vulnerable when deployed within the existing environment. The system can be secure when isolated; however, it becomes vulnerable when connected to the Internet. Machine learning (ML)-based IDSs have recently emerged as the leading intrusion detection research system. The machine learning-based IDS system may learn to make judgments without explicitly programmed and with minimal human interaction. This paper comprehensively studies intrusion detection in distributed big data systems. It presents intrusion detection taxonomy and utilizes ML and big data analytics techniques in distributed intrusion detection systems. |
| Keywords |
| Intrusion detection system, Signature-based detection, Anomaly-based detection, Machine learning, Big data, Distributed systems. |
| Status: Abstract Accepted (Oral Presentation) |