Model determination device and method

A model training device is configured to execute the following operations. Candidate models are validated based on first adversarial validation data to generate a first precision rate corresponding to each of the candidate models, wherein the first adversarial validation data is generated by a first adversarial attack adjustment performed on validation data based on an initial model. A second adversarial attack adjustment is performed on the validation data based on the candidate models to generate second adversarial validation data corresponding to each of the candidate models respectively. The candidate models are validated based on the corresponding second adversarial validation data to generate a second precision rate corresponding to each of the candidate models. At least one output model is selected from the candidate models based on the first precision rate and the second precision rate corresponding to each of the candidate models.