Abstract: Techniques are generally described for generation of photorealistic synthetic image data. A generator network generates first synthetic image data. A first class of image data represented by a first portion of the first synthetic image data is detected and the first portion is sent to a first discriminator network. The first discriminator network generates a prediction of whether the first portion of the first synthetic image data is synthetically generated. A second class of image data represented by a second portion of the first synthetic image data is detected and the second portion is sent to a second discriminator network. The second discriminator network generates a prediction of whether the second portion of the first synthetic image data is synthetically generated. The generator network is updated based on the predictions of the discriminators.

Abstract: Systems, methods, and computer-readable media are disclosed for predictive user segmentation modeling and browsing interaction analysis for digital advertising. In one embodiment, an example method may include identifying a target consumer segment, generating a predictive user behavior model for the target consumer segment based at least in part on selected user data, and receiving an indication that a user is browsing a website. Example methods may include generating a first customer score for the user using the predictive user behavior model in real-time, and determining that the first customer score meets a consumer segment modification threshold for the target consumer segment.

Abstract: Various approaches discussed herein enable techniques for managing privacy with respect to location-based operations, for example by receiving point of interest (POI) data corresponding to location data such as global positioning service (GPS) data at a computing device along with various location-based rules, which when satisfied, result in attribution events being generated that indicate various characteristics associated with POIs in the POI data. The attribution events are then sent to a server without compromising the location privacy of the computing device, because the location of the computing device is not included with the attribution events.

Abstract: Various approaches discussed herein enable techniques for managing privacy with respect to location-based operations, for example by receiving point of interest (POI) data corresponding to location data such as global positioning service (GPS) data at a computing device along with various location-based rules, which when satisfied, result in attribution events being generated that indicate various characteristics associated with POIs in the POI data. The attribution events are then sent to a server without compromising the location privacy of the computing device, because the location of the computing device is not included with the attribution events.

Abstract: Various embodiments pertain to techniques for measuring a user's privacy level as a user interacts with various web services. In various embodiments, entities with which the user interacts are detected and sensitive information shared by the user is logged to determine what a given entity knows about the user. In some embodiments, sensitive information that is shared by a user can be processed using a predictive algorithm to ascertain a user's level of privacy. When a user's identity is predicted by the algorithm, a user can be alerted to the loss of anonymity. In various embodiments, user-defined areas of anonymity can be used to measure a user's definition of privacy. In some embodiments, alerts can also be provided to the user when a new, previously undisclosed, piece of information is shared by the user.

Abstract: Various approaches discussed herein enable techniques for managing privacy with respect to location-based operations, for example by receiving point of interest (POI) data corresponding to location data such as global positioning service (GPS) data at a computing device along with various location-based rules, which when satisfied, result in attribution events being generated that indicate various characteristics associated with POIs in the POI data. The attribution events are then sent to a server without compromising the location privacy of the computing device, because the location of the computing device is not included with the attribution events.

Abstract: Various embodiments pertain to techniques for measuring a user's privacy level as a user interacts with various web services. In various embodiments, entities with which the user interacts are detected and sensitive information shared by the user is logged to determine what a given entity knows about the user. In some embodiments, sensitive information that is shared by a user can be processed using a predictive algorithm to ascertain a user's level of privacy. When a user's identity is predicted by the algorithm, a user can be alerted to the loss of anonymity. In various embodiments, user-defined areas of anonymity can be used to measure a user's definition of privacy. In some embodiments, alerts can also be provided to the user when a new, previously undisclosed, piece of information is shared by the user.

Abstract: Various approaches discussed herein enable techniques for managing privacy with respect to location-based operations, for example by receiving point of interest (POI) data corresponding to location data such as global positioning service (GPS) data at a computing device along with various location-based rules, which when satisfied, result in attribution events being generated that indicate various characteristics associated with POIs in the POI data. The attribution events are then sent to a server without compromising the location privacy of the computing device, because the location of the computing device is not included with the attribution events.

Abstract: Various embodiments pertain to techniques for measuring a user's privacy level as a user interacts with various web services. In various embodiments, entities with which the user interacts are detected and sensitive information shared by the user is logged to determine what a given entity knows about the user. In some embodiments, sensitive information that is shared by a user can be processed using a predictive algorithm to ascertain a user's level of privacy. When a user's identity is predicted by the algorithm, a user can be alerted to the loss of anonymity. In various embodiments, user-defined areas of anonymity can be used to measure a user's definition of privacy. In some embodiments, alerts can also be provided to the user when a new, previously undisclosed, piece of information is shared by the user.

Abstract: Various embodiments pertain to techniques for measuring a user's privacy level as a user interacts with various web services. In various embodiments, entities with which the user interacts are detected and sensitive information shared by the user is logged to determine what a given entity knows about the user. In some embodiments, sensitive information that is shared by a user can be processed using a predictive algorithm to ascertain a user's level of privacy. When a user's identity is predicted by the algorithm, a user can be alerted to the loss of anonymity. In various embodiments, user-defined areas of anonymity can be used to measure a user's definition of privacy. In some embodiments, alerts can also be provided to the user when a new, previously undisclosed, piece of information is shared by the user.

Abstract: Various embodiments pertain to techniques for measuring a user's privacy level as a user interacts with various web services. In various embodiments, entities with which the user interacts are detected and sensitive information shared by the user is logged to determine what a given entity knows about the user. In some embodiments, sensitive information that is shared by a user can be processed using a predictive algorithm to ascertain a user's level of privacy. When a user's identity is predicted by the algorithm, a user can be alerted to the loss of anonymity. In various embodiments, user-defined areas of anonymity can be used to measure a user's definition of privacy. In some embodiments, alerts can also be provided to the user when a new, previously undisclosed, piece of information is shared by the user.

Abstract: Various embodiments pertain to techniques for measuring a user's privacy level as a user interacts with various web services. In various embodiments, entities with which the user interacts are detected and sensitive information shared by the user is logged to determine what a given entity knows about the user. In some embodiments, sensitive information that is shared by a user can be processed using a predictive algorithm to ascertain a user's level of privacy. When a user's identity is predicted by the algorithm, a user can be alerted to the loss of anonymity. In various embodiments, user-defined areas of anonymity can be used to measure a user's definition of privacy. In some embodiments, alerts can also be provided to the user when a new, previously undisclosed, piece of information is shared by the user.

Abstract: Various embodiments pertain to techniques for measuring a user's privacy level as a user interacts with various web services. In various embodiments, entities with which the user interacts are detected and sensitive information shared by the user is logged to determine what a given entity knows about the user. In some embodiments, sensitive information that is shared by a user can be processed using a predictive algorithm to ascertain a user's level of privacy. When a user's identity is predicted by the algorithm, a user can be alerted to the loss of anonymity. In various embodiments, user-defined areas of anonymity can be used to measure a user's definition of privacy. In some embodiments, alerts can also be provided to the user when a new, previously undisclosed, piece of information is shared by the user.

Abstract: Systems, methods, and computer storage media having computer-executable instructions embodied thereon that utilize images to generate identifiers of entities and to determine various relationships between entities and web pages are described. A collection of class images that represent various people and non-people entities deemed relevant for tracking user behavior is generated. Given a class image that represents an entity, an image identifier comprising unique feature vectors for that class image is generated. Given an arbitrary web page, all the images embedded on the web page are analyzed. Each embedded image is compared to the image identifiers of the collection of class images to determine whether or not any entities of interest appear in the embedded images of the web page. If relevant entities do appear on the web page, various associations can be made between the entities found on the page, and between the uniform resource locator (URL) of the web page where the entities appear.

Abstract: Systems, methods, and computer storage media having computer-executable instructions embodied thereon that utilize images to generate identifiers of entities and to determine various relationships between entities and web pages are described. A collection of class images that represent various people and non-people entities deemed relevant for tracking user behavior is generated. Given a class image that represents an entity, an image identifier comprising unique feature vectors for that class image is generated. Given an arbitrary web page, all the images embedded on the web page are analyzed. Each embedded image is compared to the image identifiers of the collection of class images to determine whether or not any entities of interest appear in the embedded images of the web page. If relevant entities do appear on the web page, various associations can be made between the entities found on the page, and between the uniform resource locator (URL) of the web page where the entities appear.

Abstract: Embodiments of the present invention relate to systems, methods, and computer-storage media for providing a method of presenting advertisements to a target group of potential consumers generated from a group of seed consumers. In one embodiment, a target list request is received from an advertiser. A set of seed consumers associated with the advertiser is then determined. A set of potential consumers is then determined based on the set of seed consumers. Further, a subset of the set of potential consumers is determined, each potential consumer of the subset having a common characteristic. A target list of potential consumers is then generated comprising at least a portion of the subset of potential consumers. The target list of potential consumers is then provided to the advertiser.

Abstract: Methods, systems, and computer-readable media for categorizing sender domains are provided. An advertisement platform includes targeting components, databases, mail servers, and client devices. Recipients interact with the client devices to receive electronic mail from the mail servers. The mail servers store records of sender domains where the recipient performed a specified action to a message having a sender domain. The mail server transmits a log of the sender domains, actions, and an anonymous identifier for the recipient to the targeting system. The targeting components extract the sender domains that are used by the advertisement platform to communicate to the database to retrieve advertisement categories that correspond to the sender domains. The advertisement categories are used by the advertisement platform to direct content, including advertisements, to the recipients via the anonymous identifier.

Abstract: A system that facilitates targeted advertising is described in detail herein. The system includes a receiver component that receives user data that includes historical searching and browsing activity of a user. A profile generator component generates a user profile based at least in part upon a subset of the user data, wherein the user profile includes a plurality of keywords, wherein at least one keyword in the plurality of keywords is assigned a score that is indicative of a probability that an advertisement corresponding to the keyword will be monetized.

Abstract: Detecting an attack on an authentication service. A first memory area is configured to store data relating to a plurality of requests communicated to an authentication service from a plurality of user agents. A second memory area is configured to store a predefined pattern of one or more requests. The predefined pattern characterizes an attack. A processor searches the stored data as a function of a query variable to identify at least one of the plurality of the requests communicated from at least one of the plurality of the user agents and compares the stored data associated with each of the identified requests with the predefined pattern to determine whether the identified request indicates the attack characterized by the predefined pattern. Other aspects of the invention are directed to computer-readable media for use with detecting the attack on the authentication service.

Abstract: Detecting an attack on an authentication service. A first memory area is configured to store data relating to a plurality of requests communicated to an authentication service from a plurality of user agents. A second memory area is configured to store a predefined pattern of one or more requests. The predefined pattern characterizes an attack. A processor searches the stored data as a function of a query variable to identify at least one of the plurality of the requests communicated from at least one of the plurality of the user agents and compares the stored data associated with each of the identified requests with the predefined pattern to determine whether the identified request indicates the attack characterized by the predefined pattern. Other aspects of the invention are directed to computer-readable media for use with detecting the attack on the authentication service.