Abstract: Disclosed is a system for processing data streams that includes a parallel processor and a netflow aggregator module to generate a storage representation for data packets. Each storage representation includes segments of information about the data packet, the segments of information including information about a communication protocol specification related to the data packet. The netflow aggregator module generates a composite index to identify a data packet association characteristic for each data packet and stores the composite index in a segment of the storage representation. The netflow aggregator module groups data packets by their composite index. The netflow aggregator module generates a session flow identifier by identifying a beginning and/or end of a transmission netflow for each data packet having the same data packet association characteristic. The netflow aggregator module aggregates and orders the data packets having the same session flow identifiers into a flow channel.

Abstract: A method for detecting and/or identifying a cyber-attack on a network can include segmenting the network using a segmentation method with machine learning to generate one or more network segments; assigning a score to a data point within each network segment based on a presence or absence of an identified anomalous behavior of the data point; analyzing network data flow, via behavioral modeling, to provide a context for characterizing the anomalous behavior; combining, via a reinforcement learning agent, outputs of the segmentation method with behavioral modelling and assigned score to detect and/or identify a cyber-attack; providing one or more alerts to an analyst; receiving an analyst assessment of an effectiveness of the detection and/or identification; and providing the analyst assessment as feedback to the reinforcement learning agent.

Abstract: A method for detecting and/or identifying a cyber-attack on a network can include segmenting the network using a segmentation method with machine learning to generate one or more network segments; assigning a score to a data point within each network segment based on a presence or absence of an identified anomalous behavior of the data point; analyzing network data flow, via behavioral modeling, to provide a context for characterizing the anomalous behavior; combining, via a reinforcement learning agent, outputs of the segmentation method with behavioral modelling and assigned score to detect and/or identify a cyber-attack; providing one or more alerts to an analyst; receiving an analyst assessment of an effectiveness of the detection and/or identification; and providing the analyst assessment as feedback to the reinforcement learning agent.