Machine Learning Enhanced Access Control for Big Data

Access Controls (AC) are one of the main means of defense in IT systems, unfortunately, Big Data Systems are still lacking in this field, the current well-known ACs are vulnerable and can be compromised because of policy misconfiguration and lack of contextuality. In this article we propose a Machine Learning approach to optimize ABAC (Attribute Based Access Control) with the aim to reduce the attacks that are overlooked by the hardcoded policies (i.e: users abusing their privileges). We use unsupervised learning outlier detection algorithms to detect anomalous user behaviors. The Framework was implemented in Python and its performance tested using the UNSW-NB15 Data Set.