Implementing machine learning for data breach detection

• Autor(a) principal: Gama, José Martim Mendes de Vasconcellos Rebelo da
• Data de Publicação: 2020
• Tipo de documento: Dissertação
• Idioma: eng
• Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
• Texto Completo: http://hdl.handle.net/10362/111618
• topic: Machine Learning; User and entity behavior analytics; Anomaly detection; Domínio/Área Científica::Ciências Sociais::Economia e Gestão

Privata. ai is a User and Entity Behavior Analytics (UEBA) application used for the detection of data breaches in an organization. By tracking down the usual access to personal and sensitive data, it becomes much easier to detect an outlier. These anomalies could result in a real threat to the company’s data security and must, therefore, be promptly detected and addressed. This paper focuses on the managerial challenges that arise from the increasing threat of data breaches and how machine learning could help in protecting organizations from them. For this purpose, large part of the challenge came from understanding the unique specificities of these attacks and finding an appropriate machine learning method to detect them. Given the fact that the data used to train the models was randomly generated, the results should be taken with caution. Nevertheless, the models used for this paper should be taken as a basis for the future development of the software.