Machine Learning and Static Analysis for Building Software Verification Portfolios

Are you interested in Machine Learning and Formal Methods?

We are looking for students to work on Verifolio, our machine learning-based portfolio software verifier.
Verifolio uses static analysis and machine learning to automatically pick a suitable verification tool for a given verification task.

Currently, Verifolio is trained and evaluated on data from the Intl. Competition on Software Verification (SV-COMP) using Support Vector Machines (SVM). It outperforms any standalone software verifier in the competition. We are looking for motivated students who will

  • update Verifolio to the latest editions of SV-COMP (SV-COMP’17 & ’18)
  • facilitate further machine learning algorithms, in particular (deep) neural networks
  • advance our understanding of the trained model (e.g., for feature selection)
  • implement new static analyses to extend our feature set
  • improve our infrastructure for running experiments

 

[Contact Florian ZulegerThomas Pani]

Latest News

LogicLounge in memoriam Helmut Veith

Will robots take away your job? In memory of Helmut Veith, this year’s Conference on Computer Aided Verification (CAV), which takes place in Toronto, will feature a LogicLounge on the effect of automation and artificial intelligence on our jobs.

Continue reading

Questions answered by Leslie Lamport

Leslie Lamport is going to answer questions about a Mathematical View of Computer Systems in Informatikhörsaal on Tuesday at 6pm. Check the announcement at the VCLA website and do not forget to watch the lecture beforehand.

Continue reading

Full news archive