The project addresses the problem of explaining neural networks
Publications:
- Space Explanation of Neural Network Classification, Faezeh Labbaf, Tomáš Kolárik, Martin Blicha, Grigory Fedyukovich, Michael Wand, and Natasha Sharygina, CAV 2025.
Formal Verification and Security Lab
The Lab is funded by Swiss National Science Foundation, Foundation Tasso, Hasler Foundation, EU-COST initiative and EU FP7/Pincette.
