Compositional Falsification of Cyber-Physical Systems with Machine Learning Components

Understand

Cyber-physical systems (CPS), such as automotive systems, are starting to include sophisticated machine learning (ML) components.

• Their correctness, therefore, depends on properties of the inner ML modules.
• While learning algorithms aim to generalize from examples, they are only as good as the examples provided, and recent efforts have shown that they can produce inconsistent output under small adversarial perturbations.
• This raises the question: can the output from learning components can lead to a failure of the entire CPS? In this work, we address this question by formulating it as a problem of falsifying signal temporal logic (STL) specifications for CPS with ML components.