Concept Enforcement and Modularization for the ISO 26262 Safety Case of Neural Networks

The ability to formulate formally verifiable requirements is crucial for the safety verification of software units in the automotive industries. However, it is very restricted for complex perception tasks involving deep neural networks (DNNs) due to their black-box character. For a solution we propose to identify or enforce human interpretable concepts as intermediate output of the DNN. Two effects are expected: Requirements can be formulated using these concepts. And the DNN is modularized, thus reduces complexity and therefore easing a safety case. A research project proposal for a PhD thesis is sketched in the following.