Simon Lutz

Simon Lutz, Daniel Neider, Rajarshi Roy

Virtually all verification and synthesis techniques assume that the formal specifications are readily available, functionally correct, and fully match the engineer's understanding of the given system. However, this assumption is often unrealistic in practice: formalizing system requirements is notoriously difficult, error-prone, and requires substantial training. To alleviate this severe hurdle, we propose a fundamentally novel approach to writing formal specifications, named specification sketching for Linear Temporal Logic (LTL). The key idea is that an engineer can provide a partial LTL formula, called an LTL sketch, where parts that are hard to formalize can be left out. Given a set of examples describing system behaviors that the specification should or should not allow, the task of a so-called sketching algorithm is then to complete a given sketch such that the resulting LTL formula is consistent with the examples. We show that deciding whether a sketch can be completed falls into the complexity class NP and present two SAT-based sketching algorithms. We also demonstrate that sketching is a practical approach to writing formal specifications using a prototype implementation.

Simon Lutz, Daniil Kaminskyi, Florian Wittbold et al.

Automata learning is a successful tool for many application domains such as robotics and automatic verification. Typically, automata learning techniques operate in a supervised learning setting (active or passive) where they learn a finite state machine in contexts where additional information, such as labeled system executions, is available. However, other settings, such as learning from unlabeled data - an important aspect in machine learning - remain unexplored. To overcome this limitation, we propose a framework for learning a deterministic finite automaton (DFA) from a given multi-set of unlabeled words. We show that this problem is computationally hard and develop three learning algorithms based on constraint optimization. Moreover, we introduce novel regularization schemes for our optimization problems that improve the overall interpretability of our DFAs. Using a prototype implementation, we demonstrate practical feasibility in the context of unsupervised anomaly detection.