Abstract: Arrangements for dynamic variable determination and labeling are provided. In some aspects, a computing platform may receive historical user data from a plurality of data sources. The computing platform may train, using the historical user data, a machine learning model to generate a plurality of dynamic variable profiles and evaluate data to detect potential unauthorized activity. One or more dynamic variable profiles of the generated plurality of dynamic variable profiles may be associated with a user. User specific data may be received and may include user identifying data and a request for a user event. The user specific data may be input to the machine learning model and, upon execution of the model, the model may output a determination of whether an anomaly exists in the user specific data. If an anomaly is detected, a mitigating action may be identified and transmitted to one or more computing devices for execution.

Abstract: Systems, computer program products, and methods are provided for code revision impact analysis. The method includes generating a system map based on data received from a plurality of network devices; receiving a data transmission including a text file; processing the text file via a natural language processing engine, where an output of the natural language processing engine comprises a plurality of expected updates; determining, based on the system map, at least one downstream effect of the plurality of expected updates; and performing a remedial action.

Abstract: Systems, computer program products, and methods are provided for automated detection of source code discrepancies. The method includes receiving a data transmission including a text file and a source code file; processing the source code file via a machine learning engine, where an output of the machine learning engine includes a plurality of identified updates; processing the text file via a natural language processing engine, where an output of the natural language processing engine includes a plurality of expected updates; identifying a difference between the plurality of identified updates and the plurality of expected updates; and performing a remedial action.

Abstract: Systems, computer program products, and methods are described herein for automatically classifying data based on data usage and accessing patterns in an electronic network. The present invention is configured to receive at least one query log comprising a plurality of data identifiers; generate a data identifier total based on each data identifier of the plurality of data identifiers; determine a data classification for each data identifier based on the data identifier total, wherein the data classification comprises at least one of an important classification or an unimportant classification; and generate a data catalogue comprising at least one data identifier associated with the important classification.

Abstract: Systems, computer program products, and methods are described herein for verifying authentication credentials in an electronic network. The present invention is configured to receive a first IP address associated with a first access attempt; determine a first geolocation data based on the first IP address; receive a second IP address associated with a second access attempt; determine a second geolocation data based on the second IP address; determine a geolocation variance between the first and the second geolocation data; determine, based on the geolocation variance, an indication of potential movement between the access attempts; apply, based on the indication of potential movement, a verification machine learning model to the account identifier; generate, by the verification machine learning model, a privacy score; and generate, based on the privacy score, an alert user interface component to configure a GUI of a device associated with the user of the account.

Abstract: Systems, computer program products, and methods are described herein for verifying authentication credentials in an electronic network. The present invention is configured to receive a first IP address associated with a first access attempt; determine a first geolocation data based on the first IP address; receive a second IP address associated with a second access attempt; determine a second geolocation data based on the second IP address; determine a geolocation variance between the first and the second geolocation data; determine, based on the geolocation variance, an indication of potential movement between the access attempts; apply, based on the indication of potential movement, a verification machine learning model to the account identifier; generate, by the verification machine learning model, a privacy score; and generate, based on the privacy score, an alert user interface component to configure a GUI of a device associated with the user of the account.

Abstract: Systems, computer program products, and methods are described herein for identifying unauthorized use of a user's authentication credentials to an electronic network based on non-public data access. The present invention is configured to receive a verified access attempt at a first time for a user account; receive an unverified access attempt at a second time for the user account; determine the unverified access attempt is a credential sharing event for the user account; receive unverified account access logs associated with the unverified access attempt, the unverified account access logs comprising access to non-public data; and generate an unverified data access interface component to configure a graphical user interface of a device associated with a manager of the system.

Abstract: Systems, computer program products, and methods are described herein for identifying unauthorized use of a user's authentication credentials to an electronic network based on non-public data access. The present invention is configured to receive a verified access attempt at a first time for a user account; receive an unverified access attempt at a second time for the user account; determine the unverified access attempt is a credential sharing event for the user account; determine the user account is an internal account; determine an unverified user associated with the unverified access attempt is an external user; receive unverified account access logs associated with the unverified access attempt, the unverified account access logs comprising access to non-public data; and generate an unverified data access interface component to configure a graphical user interface of a device associated with a manager of the system.

Abstract: Arrangements for dynamic variable determination and labeling are provided. In some aspects, a computing platform may receive historical user data from a plurality of data sources. The computing platform may train, using the historical user data, a machine learning model to generate a plurality of dynamic variable profiles and evaluate data to detect potential unauthorized activity. One or more dynamic variable profiles of the generated plurality of dynamic variable profiles may be associated with a user. User specific data may be received and may include user identifying data and a request for a user event. The user specific data may be input to the machine learning model and, upon execution of the model, the model may output a determination of whether an anomaly exists in the user specific data. If an anomaly is detected, a mitigating action may be identified and transmitted to one or more computing devices for execution.

Abstract: A computing platform may train, using unsupervised learning techniques, a synthetic identity detection model to detect attempts to generate synthetic identities. The computing platform may receive identity information corresponding to an identity generation request. The computing platform may use the synthetic identity detection model to: 1) generate information clusters corresponding to the identity information, 2) compare a difference between actual and expected information clusters to an anomaly detection threshold, 3) based on identifying that the number of information clusters meets or exceeds the anomaly detection threshold, generate a threat score corresponding to the identity information, 4) compare the threat score to a synthetic identity detection threshold, and 5) based on identifying that the threat score meets or exceeds the synthetic identity detection threshold, identify a synthetic identity generation attempt.

Abstract: Systems, computer program products, and methods are described herein for analyzing micro-anomalies in anonymized electronic data. The present disclosure is configured to import or retrieve a first data set, process the first data set to develop at least one event-outcome projection, define an outcome projection data set, import or receive a monitored user data set, anonymize the monitored user data set, define an avatar data set process the avatar data set, wherein the steps of import or receive a monitored user data set, anonymize the monitored user data set, and define an avatar data set are repeated one or more times.

Abstract: A device that is configured to receive user activity information that includes information about user interactions with a network device for a plurality of users. The device is further configured to input the user activity information into a first machine learning model that is configured to receive user activity information and to output a set of bad actor candidates based on the user activity information. The device is further configured to filter the user activity information based on the set of bad actor candidates. The device is further configured to input the filtered user activity information into a second machine learning model that is configured to receive the filtered user activity information and to output system exposure information that identifies network security threats. The device is further configured to identify network security actions based on the network security threats and to execute the network security actions.

Abstract: A system is configured for associating a CVE with a particular device profile is disclosed. The system receives a request from a user to associate a CVE with a particular device profile. For each device profile from a plurality of device profiles stored in a memory, the system determines feature importance values for features of each device profile. The features of each device profile include at least an operating system and a CPU architecture. The feature importance value of a corresponding feature of a device profile associated with a CVE indicates a probability of the CVE to affect the device profile with respect to that feature. The system identifies a device profile that has features with a total feature importance value above a feature importance threshold value. The system identifies a particular CVE associated with the identified device profile. The system associates the particular CVE with the particular device profile.

Abstract: Systems, computer program products, and methods are described herein for code revision impact analysis. The present disclosure is configured to generate a system map based on data received from a plurality of network devices; receive a data transmission including a text file; process the text file via a natural language processing engine, where an output of the natural language processing engine comprises a plurality of expected updates; determine, based on the system map, at least one downstream effect of the plurality of expected updates; and perform a remedial action.

Abstract: Systems, computer program products, and methods are described herein for automated detection of source code discrepancies. The present disclosure is configured to receive a data transmission including a text file and a source code file; process the source code file via a machine learning engine, where an output of the machine learning engine includes a plurality of identified updates; process the text file via a natural language processing engine, where an output of the natural language processing engine includes a plurality of expected updates; identify a difference between the plurality of identified updates and the plurality of expected updates; and perform a remedial action.

Abstract: A device that is configured to receive user activity information from a network device. The user activity information includes information about user interactions with the network device for a plurality of users. The device is further configured to input the user activity information into a machine learning model. The machine learning model is configured to receive user activity information and to output a set of bad actor candidates based on the user activity information. The set of bad actor candidates identifies one or more users from among the plurality of users. The device is further configured to receive the set of bad actor candidates from the machine learning model and to output the set of bad actor candidates.

Abstract: Systems, computer program products, and methods are described herein for analyzing micro-anomalies in anonymized electronic data. The present disclosure is configured to import or retrieve a first data set, process the first data set to develop at least one event-outcome projection, define an outcome projection data set, import or receive a monitored user data set, anonymize the monitored user data set, define an avatar data set process the avatar data set, wherein the steps of import or receive a monitored user data set, anonymize the monitored user data set, and define an avatar data set are repeated one or more times.

Abstract: Systems, computer program products, and methods are described herein for processing data using an optimized machine learning architecture. The present disclosure is configured to monitor usage data for a plurality of network devices; analyze the usage data using a first machine learning engine; determine, based on an output of the first machine learning engine, at least one data trend; and instruct a second machine learning engine to analyze local data associated with the at least one data trend, wherein the second machine learning engine is hosted on a first network device of the plurality of network devices.

Abstract: Systems, computer program products, and methods are described herein for automatically classifying data based on data usage and accessing patterns in an electronic network. The present invention is configured to receive at least one query log comprising a plurality of data identifiers; generate a data identifier total based on each data identifier of the plurality of data identifiers; determine a data classification for each data identifier based on the data identifier total, wherein the data classification comprises at least one of an important classification or an unimportant classification; and generate a data catalogue comprising at least one data identifier associated with the important classification.

Abstract: A device that is configured to receive user activity information that includes information about user interactions with a network device for a plurality of users. The device is further configured to input the user activity information into a first machine learning model that is configured to receive user activity information and to output a set of bad actor candidates based on the user activity information. The device is further configured to filter the user activity information based on the set of bad actor candidates. The device is further configured to input the filtered user activity information into a second machine learning model that is configured to receive the filtered user activity information and to output system exposure information that identifies network security threats. The device is further configured to identify network security actions based on the network security threats and to execute the network security actions.