Explanation by automated reasoning using the Isabelle Infrastructure framework

Inthispaper,weproposetheuseofinteractivetheoremprov- ing for explainable machine learning. After informally motivating our proposition, we illustrate it on the dedicated application of explaining security attacks using the Isabelle Infrastructure framework and its pro- cess of dependability engineering. This formal framework and process provides the logics for specification and modeling. Attacks on security of the system are explained by specification and proofs in the Isabelle Infrastructure framework. Existing case studies of dependability engineering in Isabelle are used as feasibility studies to illustrate how dif- ferent aspects of explanations are covered by the Isabelle Infrastructure framework. Finally, we propose a research agenda on how first-class ex- planation integrated with automated reasoning will solve the problem