Abstract: In various embodiments, systems, methods, and techniques are disclosed for generating a collection of clusters of related data from a seed. Seeds may be generated based on seed generation strategies or rules. Clusters may be generated by, for example, retrieving a seed, adding the seed to a first cluster, retrieving a clustering strategy or rules, and adding related data and/or data entities to the cluster based on the clustering strategy. Various cluster scores may be generated based on attributes of data in a given cluster. Further, cluster metascores may be generated based on various cluster scores associated with a cluster. Clusters may be ranked based on cluster metascores. Various embodiments may enable an analyst to discover various insights related to data clusters, and may be applicable to various tasks including, for example, tax fraud detection, beaconing malware detection, malware user-agent detection, and/or activity trend detection, among various others.

Abstract: Systems and methods may be provided for masking data on public networks, such as social networking sites. At a publishing node, the system may monitor data input fields in a webpage that are processed by an internet browser. The system may intercept data, such as text, images, and video input at the data input fields, prior to the data being posted online on a public service provider's website. The publishing node may control which users are permitted access to the posted data by defining a policy associated with the data input field. The posted data may be transformed or tokenized to ensure that it is inaccessible to a user (or group of users) unless that user/group is granted access to the decoding key under the policy. In this way, data security and data control may be provided to a publishing user node. Data that has already been posted may be destroyed, for example, by deleting the decryption key or a token.

Abstract: A system and corresponding method gather information about browsing and purchasing behavior of web users to avoid tracking information associated with individual web browser instances. The system enables collection of historical and statistical information by legitimate interested parties to be severed from information about the behavior of a browser instance, and so too from information about the user of the browser instance. The system is configured to perform at least one of: (i) masking a web browser cookie to prevent use of the cookie to access browsing information related to a user and (ii) replace stories about sequences of browser behaviors with statistics about abstracted “story types.” A story type is a sequence of behavior types common to all web browser instances which have performed that sequence. An example embodiment uses masking and aggregation techniques, frequently, and includes a variety of industry standard security measures specially adapted to these purposes.

Abstract: Systems and methods may be provided for masking data on public networks, such as social networking sites. At a publishing node, the system may monitor data input fields in a webpage, and intercept and encode content, such as text, images, and video input at the data input fields, prior to the content being posted online on a public service provider's website. A privacy agent may process input field content to try to detect encoding markers in the input field content, which define portions of the content that are to be encoded. A third party key server may be used to store decoding keys. A URI reference to the decoding key may be used to access the decoding key by a node attempting to view the decoded version of the input field content.

Abstract: Systems and methods may be provided for masking data on public networks, such as social networking sites. At a publishing node, the system may monitor data input fields in a webpage, and intercept and encode content, such as text, images, and video input at the data input fields, prior to the content being posted online on a public service provider's website. A privacy agent may process input field content to try to detect encoding markers in the input field content, which define portions of the content that are to be encoded. A third party key server may be used to store decoding keys. A URI reference to the decoding key may be used to access the decoding key by a node attempting to view the decoded version of the input field content.

Abstract: Systems and methods may be provided for masking data on public networks, such as social networking sites. At a publishing node, the system may monitor data input fields in a webpage that are processed by an internet browser. The system may intercept data, such as text, images, and video input at the data input fields, prior to the data being posted online on a public service provider's website. The publishing node may control which users are permitted access to the posted data by defining a policy associated with the data input field. The posted data may be transformed or tokenized to ensure that it is inaccessible to a user (or group of users) unless that user/group is granted access to the decoding key under the policy. In this way, data security and data control may be provided to a publishing user node. Data that has already been posted may be destroyed, for example, by deleting the decryption key or a token.

Abstract: Embodiments are directed to methods and systems for determining the identity of a user as a person or a robot. In some embodiments, the methods and systems engage a web browser to produce a token and calculate a computation cost associated with the token production. The methods and systems use the computation cost to prove that the web browser on a device not handicapped by the computational challenge of producing tokens, which would handicap a robot. In some embodiments, the methods and systems generate a cookie based on a confirmed user purchase, and record the user identity contained in the cookie at a block chain to identify the user as a verified purchaser. The methods and systems may later retrieve the cookie and search the block chain using the user identity contained in the cookie. By locating the user identity in the block chain, the methods and systems know that the user is a verified purchaser, indicating the user to be a person, as robots cannot make purchases.

Abstract: A system and corresponding method gather information about browsing and purchasing behavior of web users to avoid tracking information associated with individual web browser instances. The system enables collection of historical and statistical information by legitimate interested parties to be severed from information about the behavior of a browser instance, and so too from information about the user of the browser instance. The system is configured to perform at least one of: (i) masking a web browser cookie to prevent use of the cookie to access browsing information related to a user and (ii) replace stories about sequences of browser behaviors with statistics about abstracted “story types.” A story type is a sequence of behavior types common to all web browser instances which have performed that sequence. An example embodiment uses masking and aggregation techniques, frequently, and includes a variety of industry standard security measures specially adapted to these purposes.

Abstract: Systems and methods for generating geographic data for map elements based on surfel data and motion data associated with a geographic region are disclosed. A computing system can obtain motion data indicative of movement of at least one object in a geographic region represented by a map. The computing system can additionally obtain surfel data indicative of one or more surface elements associated with a surface of a structure in the geographic region represented by the map. The computing system can identify an entrance of the structure based at least in part on a correlation of the surfel data and the motion data. The computing system can generate geographic data indicative of a geographic location of the entrance of the structure.

Abstract: Online retailers and advertisers typically attempt to glean information about a potential customer from his or her web browser click history. However, relying on only a potential customer's click history is not an effective means for tailoring and personalizing web content for the user in the moment of customer interaction with the web content. Obtaining information about the user's engagement with web content is critical to successful personalization of web content in real-time. The present invention provides solutions for monitoring, tracking and calculating user engagement with web content that enables successful personalization of web content in the moment of interaction.

Abstract: Systems and methods for generating geographic data for map elements based on surfel data and motion data associated with a geographic region are disclosed. A computing system can obtain motion data indicative of movement of at least one object in a geographic region represented by a map. The computing system can additionally obtain surfel data indicative of one or more surface elements associated with a surface of a structure in the geographic region represented by the map. The computing system can identify an entrance of the structure based at least in part on a correlation of the surfel data and the motion data. The computing system can generate geographic data indicative of a geographic location of the entrance of the structure.

Abstract: Systems and methods are provided for training a machine learned model on a large number of devices, each device acquiring a local set of training data without sharing data sets across devices. The devices train the model on the respective device's set of training data. The devices communicate a parameter vector from the trained model asynchronously with a parameter server. The parameter server updates a master parameter vector and transmits the master parameter vector to the respective device.

Abstract: Systems and methods may be provided for masking data on public networks, such as social networking sites. At a publishing node, the system may monitor data input fields in a webpage that are processed by an internet browser. The system may intercept data, such as text, images, and video input at the data input fields, prior to the data being posted online on a public service provider's website. The publishing node may control which users are permitted access to the posted data by defining a policy associated with the data input field. The posted data may be transformed or tokenized to ensure that it is inaccessible to a user (or group of users) unless that user/group is granted access to the decoding key under the policy. In this way, data security and data control may be provided to a publishing user node. Data that has already been posted may be destroyed, for example, by deleting the decryption key or a token.

Abstract: Embodiments are directed to methods and systems for determining the identity of a user as a person or a robot. In some embodiments, the methods and systems engage a web browser to produce a token and calculate a computation cost associated with the token production. The methods and systems use the computation cost to prove that the web browser on a device not handicapped by the computational challenge of producing tokens, which would handicap a robot. In some embodiments, the methods and systems generate a cookie based on a confirmed user purchase, and record the user identity contained in the cookie at a block chain to identify the user as a verified purchaser. The methods and systems may later retrieve the cookie and search the block chain using the user identity contained in the cookie. By locating the user identity in the block chain, the methods and systems know that the user is a verified purchaser, indicating the user to be a person, as robots cannot make purchases.

Abstract: Systems and methods may be provided for masking data on public networks, such as social networking sites. At a publishing node, the system may monitor data input fields in a webpage that are processed by an internet browser. The system may intercept data, such as text, images, and video input at the data input fields, prior to the data being posted online on a public service provider's website. The publishing node may control which users are permitted access to the posted data by defining a policy associated with the data input field. The posted data may be transformed or tokenized to ensure that it is inaccessible to a user (or group of users) unless that user/group is granted access to the decoding key under the policy. In this way, data security and data control may be provided to a publishing user node. Data that has already been posted may be destroyed, for example, by deleting the decryption key or a token.

Abstract: Device identification scoring systems and methods may be provided that can increase the reliability and security of communications between devices and service providers. Users may select and configure additional identification factors that are unique and convenient for them. These factors, along with additional environmental variables, feed into a trust score computation that weights the trustworthiness of the device context requesting communication with a service provider. Service providers rely on the trust score rather than enforce a specific identification routine themselves. A combination of identification factors selected by the user can be aggregated together to produce a trust score high enough to gain access to a given online service provider. A threshold of identification risk may be required to access a service or account provided by the online service provider.

Abstract: Systems and methods may be provided for masking data on public networks, such as social networking sites. At a publishing node, the system may monitor data input fields in a webpage, and intercept and encode content, such as text, images, and video input at the data input fields, prior to the content being posted online on a public service provider's website. A privacy agent may process input field content to try to detect encoding markers in the input field content, which define portions of the content that are to be encoded. A third party key server may be used to store decoding keys. A URI reference to the decoding key may be used to access the decoding key by a node attempting to view the decoded version of the input field content.

Abstract: Device identification scoring systems and methods may be provided that can increase the reliability and security of communications between devices and service providers. Users may select and configure additional identification factors that are unique and convenient for them. These factors, along with additional environmental variables, feed into a trust score computation that weights the trustworthiness of the device context requesting communication with a service provider. Service providers rely on the trust score rather than enforce a specific identification routine themselves. A combination of identification factors selected by the user can be aggregated together to produce a trust score high enough to gain access to a given online service provider. A threshold of identification risk may be required to access a service or account provided by the online service provider.

Abstract: Systems and methods may be provided for masking data on public networks, such as social networking sites. At a publishing node, the system may monitor data input fields in a webpage, and intercept and encode content, such as text, images, and video input at the data input fields, prior to the content being posted online on a public service provider's website. A privacy agent may process input field content to try to detect encoding markers in the input field content, which define portions of the content that are to be encoded. A third party key server may be used to store decoding keys. A URI reference to the decoding key may be used to access the decoding key by a node attempting to view the decoded version of the input field content.

Abstract: Systems and methods may be provided for masking data on public networks. At a publishing node, the system may monitor data input fields in a webpage, and intercept and encode content, such as text, images, and video input at the data input fields, prior to the content being posted online on a public service provider's website. A policy may be defined to control which users are permitted access to a key to decode the encoded content. The policy may defer to a third party policy node in determining key access. An account for a controlling entity, such as a guardian or employer, may be configured to control the encoding status of posts made by another. The controlling entity may control who has key access to decode posts made by the other account. The guardian account may be configured to have preemptive rights over posting decisions made by the minor.