Glassbox testing (also called ''white box testing'') means testing of the AI system in which the information used as the basis for designing and implementing test cases can be derived from internal information (e.g. the AI model) as well as the external inputs and the corresponding AI system's output.

ISO/IEC TR 29119-11:2020 dynamic testing (3.29) in which the tests are derived from an examination of the structure of the test item (3.107) (SOURCE: ISO/IEC 29119-1:2022, 3.80)