Loading patent…
AssigneeInternational Business Machines Corporation
InventorsMichael Josiah Bolding, Matthew Elsner, Jian Lin, Matthew Paul Ouellette, Yun Pan
Estimating the term…
A machine learning (ML)-based technique for user behavior analysis that detects when users deviate from expected behavior. A ML model is trained using training data derived from activity data from a first set of users. The model is refined in a computationally-efficient manner by identifying a second set of users that constitute a “watch list.” At a given time, a differential data ingestion operation is then performed to incorporate data for the second set of users into the training data, while also pruning at least a portion of the data set corresponding to data associated with any user included in the first set but not in the second set. These operations update the training data used for the machine learning. The machine learning model is then refined based on the updated training data that incorporates the activity data ingested from the users identified in the watch list.
A method of training and using a machine learning model to identify suspicious behavior in a network, the machine learning model using training data that is based on data associated with a first set of users, comprising:
An apparatus, comprising:
A computer program product in a non-transitory computer readable medium for use in a data processing system to train and use a machine learning model to identify suspicious behavior in a network, the machine learning model using training data that is based on data associated with a first set of users, the computer program product holding computer program instructions that, when executed by the data processing system, are configured to:
Dependencies are inferred from the claim text.