Abstract: A system and method monitor a computer resource asset for vulnerability and security weaknesses using a smart contract and a neural network. The system comprises a processor configured to receive data from a data source, a memory configured to store current smart contract baseline data, an artificial neural network including a plurality of nodes configured as a plurality of layers to determine a new data feed in the received data and to update the current smart contract baseline data, a smart contract monitoring subsystem configured to monitor a computer resource asset using the current smart contract baseline data, and a remediation subsystem configured to remediate access of the computer resource asset to a computer network. The method implements the system.

Abstract: Configuration monitoring is performed using a computer-based system and method by identifying misconfigured settings through the collection of large amounts of configuration data from diverse sources. The configuration data is then analyzed to identify misconfigured items. Automation of such configurations is implemented using machine learning to analyze existing configurations as well as new configurations. By using machine learning, the computer-based system and method can predict a pass state or a fail state of the configuration of a newly connected system in an organization. A logistic regression classifier is trained using old complying configuration data and data reflecting industry standards. The trained classifier can predict and classify whether a new configuration passes or fails the industry standards based on the training data of old configuration data.

Abstract: A system, a method, and a computer program remediate a risk of a computing resource located in a computer network that has a plurality of other computing resource assets each having an associated risk. Data associated with a first computing resource is received, and a first risk framework is selected from among a plurality of risk frameworks. A risk score is calculated based on the received data and the selected first risk framework, and a first risk rating is determined based on the risk score. The first risk rating is compared against a zone risk rating to determine whether the first risk rating is greater than the zone risk rating, and the first risk rating is replaced by the zone risk rating when the zone risk rating is greater than the first risk rating. The cybersecurity risk of the first computing resource is remediated according to the first risk rating.

Abstract: Systems, methods, and computer-readable media for monitoring a computer network for threats using OLAP cubes are disclosed. In one embodiment, a method of monitoring a computer network for threats includes receiving, from a plurality of computing devices on the network, dataset data, asset data, and temporal data, and storing, in an online analytical processing cube for each computing device of the plurality of computing devices, the dataset data within a dataset dimension, the asset data within an asset dimension, and the temporal data within a temporal dimension. The method further includes searching one or more online analytical processing cubes for correlated data within two or more of the dataset dimension, the asset dimension, and the temporal dimension satisfying an alert metric, and issuing an alert when correlated data satisfies the alert metric.

Abstract: Systems, methods, and computer-readable media for monitoring a computer network for threats using OLAP cubes are disclosed. In one embodiment, a method of monitoring a computer network for threats includes receiving, from a plurality of computing devices on the network, dataset data, asset data, and temporal data, and storing, in an online analytical processing cube for each computing device of the plurality of computing devices, the dataset data within a dataset dimension, the asset data within an asset dimension, and the temporal data within a temporal dimension. The method further includes searching one or more online analytical processing cubes for correlated data within two or more of the dataset dimension, the asset dimension, and the temporal dimension satisfying an alert metric, and issuing an alert when correlated data satisfies the alert metric.

Abstract: A system, a method, and a computer program remediate a risk of a computing resource located in a computer network that has a plurality of other computing resource assets each having an associated risk. Data associated with a first computing resource is received, and a first risk framework is selected from among a plurality of risk frameworks. A risk score is calculated based on the received data and the selected first risk framework, and a first risk rating is determined based on the risk score. The first risk rating is compared against a zone risk rating to determine whether the first risk rating is greater than the zone risk rating, and the first risk rating is replaced by the zone risk rating when the zone risk rating is greater than the first risk rating. The cybersecurity risk of the first computing resource is remediated according to the first risk rating.

Abstract: Configuration monitoring is performed using a computer-based system and method by identifying misconfigured settings through the collection of large amounts of configuration data from diverse sources. The configuration data is then analyzed to identify misconfigured items. Automation of such configurations is implemented using machine learning to analyze existing configurations as well as new configurations. By using machine learning, the computer-based system and method can predict a pass state or a fail state of the configuration of a newly connected system in an organization. A logistic regression classifier is trained using old complying configuration data and data reflecting industry standards. The trained classifier can predict and classify whether a new configuration passes or fails the industry standards based on the training data of old configuration data.