Network anomalies detection via event analysis and correlation by a smart system

• Autor(a) principal: Cruz, Gonçalo Monteiro
• Data de Publicação: 2022
• Tipo de documento: Dissertação
• Idioma: eng
• Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
• Texto Completo: http://hdl.handle.net/10071/27448
• topic: Data monitoring; Anomaly detection; Attack detection; SIEM; Big data; ML algorithms; Monitorização de dados; Deteção de anomalias; Deteção de ataques; Sistemas SIEM; Algoritmos ML

The multidisciplinary of contemporary societies compel us to look at Information Technology (IT) systems as one of the most significant grants that we can remember. However, its increase implies a mandatory security force for users, a force in the form of effective and robust tools to combat cybercrime to which users, individual or collective, are ex-posed almost daily. Monitoring and detection of this kind of problem must be ensured in real-time, allowing companies to intervene fruitfully, quickly and in unison. The proposed framework is based on an organic symbiosis between credible, affordable, and effective open-source tools for data analysis, relying on Security Information and Event Management (SIEM), Big Data and Machine Learning (ML) techniques commonly applied for the development of real-time monitoring systems. Dissecting this framework, it is composed of a system based on SIEM methodology that provides monitoring of data in real-time and simultaneously saves the information, to assist forensic investigation teams. Secondly, the application of the Big Data concept is effective in manipulating and organising the flow of data. Lastly, the use of ML techniques that help create mechanisms to detect possible attacks or anomalies on the network. This framework is intended to provide a real-time analysis application in the institution ISCTE – Instituto Universitário de Lisboa (Iscte), offering a more complete, efficient, and secure monitoring of the data from the different devices comprising the network.