The Learning in Verification group (LiVe Lab) focuses on the interactions of machine learning and verification. Our research includes Explainable AI, Verification of Neural Networks, Stochastic Games and Control, Probabilistic Model Checking, Temporal Logics (mainly LTL, PCTL), and Automata Theory. Our research is applicable in the Robotics, Biomedical, and Automotive domains. The team is distributed between the Masaryk University Brno, Czech Republic, and the Technical University of Munich, Germany.
News
-
April 24, 2024
We are excited to welcome eight interns joining us in May for the summer and look forward to great collaborations.
-
March 26, 2024
Congratulations to Kush Grover for successfully defending his PhD thesis!
-
December 10, 2023
The group member Florian Dorfhuber presented the work “Learning Attack Trees by Genetic Algorithms” at ICTAC Conference in Lima, Peru.
-
December 09, 2023
The webpage has been created.
Research Areas
Concurrent Stochastic Games
We develop techniques for the verification of concurrent stochastic games which extend turn-based stochastic games by allowing players to select actions simultaneously in each state, reflecting more realistic scenarios of interactive agents acting concurrently.
Projects
FSCs for POMDPs
Finding compact and explainable representations of strategies for POMDPs using finite state controllers.
Fuzzy Path Logic
We develop a logic over signals in which it is easier to specify preferences using fuzzy paths. We developed the logic so that it is more amenable to learning.
SemML
In this project we develop learning-based exploration heuristics for LTL Synthesis that exploit the semantic labelling of the underlying Automaton/Game.
MONITIZER
We create a tool (Monitizer) that optimizes monitors on a NN for a specific task.
dtControl
Represent controllers as decision trees. Improve memory footprint, boost explainability while preserving guarantees.
Automata Tutor is an online teaching tool that aids instructors and students in large courses on automata and formal languages with many different exercise types.
Team
Professor
Administrative Staff
PostDocs
