International Business Machines Corporation

Abigail Goldsteen

Ariel Farkash

Micha Gideon Moffie

Ron Shmelkin

Gilad Ezov

Boris Rozenberg

Ron Ben-Natan

Igor Gokhman

Tamar Domany

Omri Soceanu

Lev Greenberg

Ury Segal

Sima Nadler

Nadav Yosef Har'el

Ksenya Kveler

Muhammad Barham

Yuval Hager

Igor Gorkhman

An embodiment analyzes a predictive model and its input data for the predictive model using an explainability algorithm resulting in a feature importance value of a feature. The embodiment analyzes feature values of the feature using a generalization function resulting in a set of candidate feature values. The embodiment determines an alternative feature based on the set of candidate feature values, wherein the alternative feature is a generalization of the feature. The embodiment compares an accuracy of the predictive model to a threshold performance value and, responsive to the accuracy being above the threshold performance value, maps feature values in the input data that are in the set of candidate feature values to a generalized representative value in the generalized domain.

Data minimization using global model explainability

A method, apparatus and a product for data generalization for predictive models. The method comprising: obtaining a training dataset that comprises a plurality of training instances and predicted labels thereof, wherein each training instance is a valuation of a set of features, wherein the set of features comprises a feature having a domain, wherein the predicted label of each training instance is a label predicted thereto by a predictive model; training an auxiliary model using the training dataset; based on the auxiliary model, determining an alternative set of features that is a generalization of the set of features, wherein the alternative set of features comprises a generalized feature having a generalized domain, wherein each value in the generalized domain corresponds to one or more values in the domain; obtaining a generalized instance having a valuation of the alternative set of features; and determining a label for the generalized instance.

Data generalization for predictive models

A method, computer system, and a computer program product for testing a data removal from a trained machine learning model trained with a training data set are provided. A new machine learning model is trained by using an altered data set that includes training data from the training data set. The altered data set is without removal data. A first forgetting mechanism is applied to the trained machine learning model to form a first revised machine learning model. The applying includes removing the removal data from the trained machine learning model. A first membership leakage quantification on the first revised machine learning model is performed to quantify a first membership leakage of the removal data and that uses the new machine learning model for comparison. A first leakage score is determined from the first membership leakage quantification to test the forgetting mechanism.

Membership leakage quantification to verify data removal

A method, computer system, and a computer program product for personal data discovery is provided. The present invention may include determining at least one feature used to train a target machine learning (ML) model. The present invention may also include mapping the determined at least one feature to at least one location of a data store including at least one personal data associated with the determined at least one feature. The present invention may further include retrieving a data record of the at least one personal data associated with the mapped at least one feature from the at least one location of the data store. The present invention may also include determining that the target ML model includes a trace of the retrieved data record. The present invention may further include marking the target ML model as containing the at least one personal data.

Discovery of personal data in machine learning models

An example system includes a processor to receive training data and predictions on the training data of a trained machine learning model to be anonymized. The processor is to generate generalized data from training data based on the predictions of the trained machine learning model on the training data. The processor is to train an anonymized machine learning model using the generalized data.

Training anonymized machine learning models via generalized data generated using received trained machine learning models

A method, apparatus and a product for data generalization for predictive models. The method comprising: based on a labeled dataset, determining a plurality of buckets, each of which has an associated label; determining a plurality of clusters, grouping similar instances in the same bucket; based on the plurality of clusters, determining an alternative set of features comprising a set of generalized features, wherein each generalized feature corresponds to a cluster of the plurality of clusters, wherein a generalized feature that corresponds to a cluster is indicative of the instance being mapped to the corresponding cluster; obtaining a second instance; determining a generalized second instance that comprises a valuation of the alternative set of features for the second instance; and based on the generalized second instance, determining a label for the second instance.

Embodiments of the present systems and methods may provide techniques for verifying the correct application purpose for applications that serve multiple purposes and to determine the correct purpose for each requested data access. For example, in an embodiment, a method for controlling application access to data implemented in a computer comprising a processor, memory accessible by the processor, and computer program instructions stored in the memory and executable by the processor may comprise: receiving an application comprising a plurality of application parts, each application part associated with a declared data access purpose and generating a cryptographic certificate for each application part to be certified by determining whether a declared data access purpose for each application part to be certified is correct and the only data access purpose for that part, wherein the declared purpose is included in purpose information associated with each application part to be certified.

Verifying purpose of data usage at sub-application granularity

A method of limiting data usage for certified purposes by using functional encryption, comprising: receiving from a software publisher an application code and declared privacy information, the declared privacy information specifies at least one declared usage for at least one data type; analyzing the application's usage of data collected by the application, to identify an actual usage of the at least one data type by a function; identifying when the actual usage is compliant with the at least one declared usage according to the analysis; in response to the identification, creating a pair of a public key and a master private key; creating a function private key for the function using the master private key; and sending the function private key to the software publisher to be used for operating the function on data which is encrypted using the public key.

Data protection using functional encryption

Embodiments of the present systems and methods may provide data watermarking without reliance on error-tolerant fields, thereby providing for the incorporation of watermarks in data that was not considered suitable for watermarking. For example, in an embodiment, a computer-implemented method for watermarking data may comprise inserting watermark data into a field that requires format-preserving encryption.

Method for watermarking through format preserving encryption

A method of creating an application purpose certificate, comprising: receiving from a software publisher an application code and declared privacy information, the declared privacy information includes at least one allowed usage purpose for each of a plurality of data types; analyzing the application's usage of data of each of the plurality of data types; verifying the usage is compliant with the least one allowed usage purpose according to the analysis; creating an encrypted digital purpose certificate, the digital purpose certificate is unique for the application code; and sending the digital purpose certificate to the software publisher to be bundled with the application code and a publisher authentication certificate.

Digital certificate for verifying application purpose of data usage

A data security method including creating a token-including plaintext by including a predefined token into a plaintext, generating a cyphertext by encrypting the token-including plaintext using format-preserving encryption, generating a decrypted cyphertext by decrypting an input text, determining whether the decrypted cyphertext includes a first predefined token, if the decrypted cyphertext includes the first predefined token, recreating the plaintext by removing the first predefined token from the decrypted cyphertext, and if the decrypted cyphertext does not include the first predefined token, using the input text as the plaintext.

Data security system with identifiable format-preserving encryption

In an approach to masking data in a software application associated with a mobile computing device, one or more computer processors receive a request to display data in a software application on a mobile computing device. The one or more computer processors determine whether one or more masking rules apply to the data, where determining whether one or more masking rules apply to the data is performed by an instrumentation of application binary of the software application. In response to determining that one or more masking rules apply to the data, the one or more computer processors mask, based on the one or more masking rules, the data, where masking is performed by the instrumentation of application binary of the software application.

Masking sensitive data in mobile applications

Methods, computing systems and computer program products implement embodiments of the present invention that include defining, for a data masking engine executing in a platform as a service (PaaS) based software environment, one or more data masking rules. Upon detecting, by the data masking engine, data processed by a software application executing within the PaaS based software environment and in accordance with a given data masking rule, the data masking engine can perform a data masking operation on the data.

Seamless data masking for PaaS based applications

A method comprising using at least one hardware processor for: receiving input from a user with respect to masking of a data element in one or more documents of a java script object notation (JSON) type, wherein the input comprises: an identifier of the data element, and one or more constraints for masking the data element based on the hierarchy of the one or more documents of the JSON-type; and generating a masking rule for the one or more documents of the JSON-type based on the input.

Masking data within JSON-type documents

Machines, systems and methods for remotely provisioning computing power over a communications network are provided. The method may comprise selecting one or more tasks being executed on a first computing system to be migrated for execution on a second computing system connected to the first computing system by way of a communications network; determining a first point of execution reached during the execution of at least a selected task on the first computing system prior to the selected task being migrated for execution to the second computing system; migrating the selected task to the second computing system, wherein the second computing system continues to execute the selected task from the first point of execution; and monitoring the connection between the first computing system and the second computing system so that in response to detecting a disconnection, execution of the selected task continues seamlessly.

Growing community of inventors

Haifa, Israel

Abigail Goldsteen