Privacy preserving evaluation of sensitive user features for anomaly detection
Techniques are provided for centralized processing of sensitive user data. One method comprises obtaining, by a service provider, values of predefined features based at least in part on personal information of a user, wherein the values of the predefined features are computed by the user; and processing, by the service provider, the values of the predefined features based on the personal information to detect one or more predefined anomalies associated with the user and/or a device of the user. The predefined anomalies comprise, for example, a risk anomaly, a security level anomaly, a fraud likelihood anomaly, an identity assurance anomaly, and/or a behavior anomaly. The predefined features relate to, for example, a location of the user and/or device-specific information for a device of the user.
1. A method, comprising:
obtaining, by at least one processing device of a service provider, values of one or more predefined features based at least in part on personal information of a given remote user, wherein the values of the one or more predefined features are computed by at least one processing device of the given remote user, wherein at least one of the values of the predefined features is categorized into a discrete category of a plurality of discrete categories, by the at least one processing device of the given remote user, prior to providing the values of the one or more predefined features to the service provider, such that the service provider cannot access the personal information of the given remote user associated with the at least one value of the one or more predefined features, wherein the categorization of the at least one value of the one or more predefined features by the at least one processing device of the given remote user is based at least in part on an evaluation of dynamic contextual data by the at least one processing device of the given remote user, wherein the dynamic contextual data is used for the categorization of the at least one value of the one or more predefined features and is provided to the at least one processing device of the given remote user by the at least one processing device of the service provider; and
processing, by the at least one processing device of the service provider, the values of the one or more predefined features based at least in part on personal information to detect one or more predefined anomalies associated with one or more of the given remote user and the at least one processing device of the given remote user.
2. The method of claim 1 , wherein the one or more predefined anomalies associated with one or more of the given remote user and the at least one processing device of the given remote user comprise one or more of a risk anomaly, a security level anomaly, a fraud likelihood anomaly, an identity assurance anomaly, and a behavior anomaly.
3. The method of claim 1 , wherein the at least one processing device of the service provider communicates with the at least one processing device associated with the given remote user to provide an updated data transformation configuration needed for calculation of the values of the one or more predefined features.
4. The method of claim 1 , wherein the at least one processing device associated with the given remote user performs a data normalization comprising one or more of setting one or more missing values, performing one or more predefined numerical transformations and performing one or more predefined pre-processing operations.
5. The method of claim 1 , wherein the at least one processing device associated with the given remote user performs a data enrichment to improve a quality of one or more of user data and the one or more predefined features.
6. The method of claim 1 , wherein the one or more predefined features based at least in part on the personal information of the given remote user relate to one or more of a location of the given remote user and device-specific information for a device of the user.
7. The method of claim 1 , wherein the obtaining comprises the at least one processing device of the given remote user sending the values of the one or more predefined features based at least in part on personal information to the service provider over an encrypted channel.
8. The method of claim 1 , wherein the at least one processing device of the service provider computes one or more additional features not associated with personal information of the given remote user.
9. The method of claim 1 , wherein the at least one processing device of the service provider initiates one or more of predefined remedial steps and predefined mitigation steps to address the detected predefined anomalies.
10. An apparatus comprising:
at least one processing device comprising a processor coupled to a memory;
the at least one processing device corresponding to a service provider and being configured to perform the following steps:
obtaining, by at least one processing device of a service provider, values of one or more predefined features based at least in part on personal information of a given remote user, wherein the values of the one or more predefined features are computed by at least one processing device of the given remote user, wherein at least one of the values of the predefined features is categorized into a discrete category of a plurality of discrete categories, by the at least one processing device of the given remote user, prior to providing the values of the one or more predefined features to the service provider, such that the service provider cannot access the personal information of the given remote user associated with the at least one value of the one or more predefined features, wherein the categorization of the at least one value of the one or more predefined features by the at least one processing device of the given remote user is based at least in part on an evaluation of dynamic contextual data by the at least one processing device of the given remote user, wherein the dynamic contextual data is used for the categorization of the at least one value of the one or more predefined features and is provided to the at least one processing device of the given remote user by the at least one processing device of the service provider; and
processing, by the at least one processing device of the service provider, the values of the one or more predefined features based at least in part on personal information to detect one or more predefined anomalies associated with one or more of the given remote user and the at least one processing device of the given remote user.
11. The apparatus of claim 10 , wherein the one or more predefined anomalies associated with one or more of the given remote user and the at least one processing device of the given remote user comprise one or more of a risk anomaly, a security level anomaly, a fraud likelihood anomaly, an identity assurance anomaly, and a behavior anomaly.
12. The apparatus of claim 10 , wherein the at least one processing device of the service provider communicates with the at least one processing device associated with the given remote user to provide an updated data transformation configuration needed for calculation of the values of the one or more predefined features.
13. The apparatus of claim 10 , wherein the one or more predefined features based at least in part on the personal information of the given remote user relate to one or more of a location of the given remote user and device-specific information for a device of the user.
14. The apparatus of claim 10 , wherein the obtaining comprises the at least one processing device of the given remote user sending the values of the one or more predefined features based at least in part on personal information to the service provider over an encrypted channel.
15. The apparatus of claim 10 , wherein the at least one processing device of the service provider initiates one or more of predefined remedial steps and predefined mitigation steps to address the detected predefined anomalies.
16. A non-transitory processor-readable storage medium having stored therein program code of one or more software programs, wherein the program code when executed by at least one processing device of a service provider causes the at least one processing device of the service provider to perform the following steps:
obtaining, by at least one processing device of a service provider, values of one or more predefined features based at least in part on personal information of a given remote user, wherein the values of the one or more predefined features are computed by at least one processing device of the given remote user, wherein at least one of the values of the predefined features is categorized into a discrete category of a plurality of discrete categories, by the at least one processing device of the given remote user, prior to providing the values of the one or more predefined features to the service provider, such that the service provider cannot access the personal information of the given remote user associated with the at least one value of the one or more predefined features, wherein the categorization of the at least one value of the one or more predefined features by the at least one processing device of the given remote user is based at least in part on an evaluation of dynamic contextual data by the at least one processing device of the given remote user, wherein the dynamic contextual data is used for the categorization of the at least one value of the one or more predefined features and is provided to the at least one processing device of the given remote user by the at least one processing device of the service provider; and
processing, by the at least one processing device of the service provider, the values of the one or more predefined features based at least in part on personal information to detect one or more predefined anomalies associated with one or more of the given remote user and the at least one processing device of the given remote user.
17. The non-transitory processor-readable storage medium of claim 16 , wherein the one or more predefined anomalies associated with one or more of the given remote user and the at least one processing device of the given remote user comprise one or more of a risk anomaly, a security level anomaly, a fraud likelihood anomaly, an identity assurance anomaly, and a behavior anomaly.
18. The non-transitory processor-readable storage medium of claim 16 , wherein the at least one processing device of the service provider communicates with the at least one processing device associated with the given remote user to provide an updated data transformation configuration needed for calculation of the values of the one or more predefined features.
19. The non-transitory processor-readable storage medium of claim 16 , wherein the one or more predefined features based at least in part on the personal information of the given remote user relate to one or more of a location of the given remote user and device-specific information for a device of the user.
20. The non-transitory processor-readable storage medium of claim 16 , wherein the obtaining comprises the at least one processing device of the given remote user sending the values of the one or more predefined features based at least in part on personal information to the service provider over an encrypted channel.