In some instances, the disclosure provides a method for identifying access anomalies using network graphs. The method comprises obtaining access data for an entity, generating a network graph baseline profile based on the plurality of data elements, generating a network graph current profile based on the plurality of data elements, generating comparison data based on comparing the plurality of baseline network graphs with the one or more current network graphs and comparing the plurality of baseline nodes and the plurality of baseline edges with the plurality of current nodes and the plurality of current edges, determining, based on the comparison data, anomaly data comprising one or more flagged network accesses to the enterprise system, and providing the anomaly data indicating the flagged network accesses to an authentication system.

A method for processing security events by applying a rule-based alarm scheme may be provided. The method includes generating a rule index of rules and an indicator of compromise index for each of the rules. The method includes also processing the incoming security event by applying the rules, increasing a current rule counter relating to a triggered rule, and increasing a current indicator of compromise counter pertaining to the triggered rule. Furthermore, the method includes generating a pseudo security event from received data about known attacks and related indicators of compromise, processing the pseudo security events by sequentially applying the rules, increasing a current rule counter of pseudo security events, and increasing a current indicator of compromise counter for pseudo security events, and sorting the rules and sorting within each rule the indicator of compromise values in the indicator of compromise index.

A network monitoring, reporting and risk mitigation system collects events at a computing device within the local network to provide improved network security. The events are aggregated into alerts, which may be processed according to triggering definitions in order to create ARO (action, recommendations and observations) reports providing required or recommended actions to take or observations to a network administrator. The ARO reports may be processed by a remote server in order to generate contextual feedback for updating the triggering definitions.

A method for training a machine learning model using information pertaining to characteristics of upload activity performed at one or more client devices includes generating first training input including (i) information identifying first amounts of data uploaded during a specified time interval for one or more of multiple application categories, and (ii) information identifying first locations external to a client device to which the first amounts of data are uploaded. The method includes generating a first target output that indicates whether the first amounts of data uploaded to the first locations correspond to malicious or non-malicious upload activity. The method includes providing the training data to train the machine learning model on (i) a set of training inputs including the first training input, and (ii) a set of target outputs including the first target output.

A method for determining whether a power system is encountering a malicious attack is provided. The method comprises: receiving a plurality of first phasor measurement unit (PMU) measurements from a plurality of PMUs of the power system; determining a plurality of expected PMU measurements associated with a future time period based on an optimization algorithm that uses differences between a plurality of consecutive predictive entries and the plurality of first PMU measurements; receiving, from the plurality of PMUs, a plurality of second PMU measurements associated with the future time period; determining whether the power system is encountering the malicious attack based on comparing the plurality of expected PMU measurements with the plurality of second PMU measurements; and executing an action based on whether the power system is encountering the malicious attack.

Some examples relate to classifying IoT malware at a network device. An example includes receiving, by a network device, network traffic from an Internet of Things (IoT) device. Network device may analyze network parameters from the network traffic with a machine learning model. In response to analyzing, network device may classify the network traffic into a category of malware activity. Network device may determine an effectiveness of network traffic classification by measuring a deviation of the network parameters from previously trained network parameters that were used for training the machine learning model. In response to a determination that the deviation of the network parameters from the trained network parameters is more than a pre-defined threshold, network device may generate an alert highlighting the deviation, which allows a user to perform a remedial action pertaining to the IoT device.

In one or more embodiments, the disclosed systems, methods, and media include utilizing a crosswalk algorithm to identify controls (e.g., cybersecurity controls) across frameworks, and for utilizing identified controls to generate cybersecurity risk assessments. A cybersecurity module may identify one or more controls in a data structure. The process may utilize a crosswalk algorithm to determine a relatedness between the identified controls and different controls of different frameworks. The process may update the data structure with selected different controls, such that a more robust set of controls are identified when the cybersecurity module indexes into the data structure to identify particular controls. Additionally, the process may generate a risk assessment for a device/software. The process may generate a risk score for the risk assessment, and the risk score may be based on a determined compliance level for each control determined to be related to a defined risk of interest.

In an example embodiment, a combination of machine learning and rule-based techniques are used to automatically detect social engineering attacks in a computer system. More particularly, three phases of detection are utilized on communications in a thread or stream of communications: attack contextualization, intention classification, and security policy violation detection. Each phase of detection causes a score to be generated that is reflective of the degree of danger in the thread or stream of communications, and these scores may then be combined into a single global social engineering attack score, which then may be used to determined appropriate actions to deal with the attack if it transgresses a threshold.

A method and system for characterizing application layer flood denial-of-service (DDoS) attacks are provided. The method includes receiving an indication on an on-going DDoS attack directed to a protected entity; generating a dynamic applicative signature by analyzing requests received during the on-going DDoS attack, wherein the dynamic applicative signature characterizes requests generated by an attack tool executing the on-going DDoS attack; and characterizing each incoming request based on the generated dynamic applicative signature, wherein the characterization provides an indication for each incoming request whether a request is generated by the attack tool.

Domain Name System (DNS) security using process information is provided. An application accessing an internet service using a domain name is determined. Process information associated with the application along with an associated DNS query to identify an IP address associated with the domain name are identified. The process information and the associated DNS query to a DNS security service are sent. An action based on a response from the DNS security service is performed.