Risk evaluation device, data protection device, and risk evaluation method

A data protection device comprising:

• at least one memory configured to store instructions;
• and
• at least one processor configured to execute the instructions to:
• specify, for a machine learning model including a plurality of partial models, data in each of the partial models having a vulnerability to a membership inference attack;
• generate data in which the specified data has been merged;
• and
• output, for the generated data, a score having a different value to a score calculated by the plurality of partial models.

A risk evaluation method executed by a computer, the method comprising:

• acquiring target data including an explanatory variable value list and a target variable value, wherein the explanatory variable value list is a list of values of classification items representing items used in a first class classification, and the target variable value is a value that identifies a class in a second class classification;
• calculating a confidence score for each partial model of a target model, wherein the target model includes the partial model for each of a plurality of ways of performing the first class classification, wherein the partial model indicates, for each class in a class classification performed using a combination of the first class classification and the second class classification, a degree to which an element of a second set generated for each partial model from a predetermined first set is classified into the class, and wherein the confidence score indicates a degree to which the element of the second set is classified into a class in the first class classification, which is performed with respect to the explanatory variable value list included in the target data, and a class in the second classification, which is identified by the target variable value included in the target data;
• and
• evaluating a possibility that the target data is included in the first set based on the confidence score of each partial model.