Amazon Technologies, Inc.

Aaron Flatten

Shane Anil Pereira

A first instance of an event management system monitors event data corresponding to a first group of users in a cloud computing system. Using a first machine learning (ML) algorithm, the first instance detects an anomalous event from the event data. The first ML algorithm is trained using historical event data. A second instance of the event management system is created and a copy of the first ML algorithm is added to the second instance. The second instance monitors second event data corresponding to a second group of users in the cloud computing system. Using the copy of the first ML algorithm, the second instance detects a second anomalous event from the second event data.

Threat detection system with machine models for accounts within an organization unit

A processing device receives a request to create a second account in a cloud computing system having multiple web services. The request specifies an organization unit (OU) associated with a first account of the cloud computing system. A first instance of a threat detection service monitors activity data associated with the first account and detects anomalous activity by the first account using a first machine learning (ML) model. The processing device creates the second account and attaches the second account to the OU. The processing device generates a second ML model for the second account using at least a portion of the first ML model and monitors subsequent activity data associated with the second account using the second ML model to detect anomalous activity by the second account.

Growing community of inventors

Portland, OR, United States of America

Aaron Flatten