Neural Network Verification

Provably Safe Neural Network Controllers via Differential Dynamic Logic
Provably Safe Neural Network Controllers via Differential Dynamic Logic

We present the first approach for the combination of differential dynamic logic (dL) and NN verification. By joining forces, we can exploit the efficiency of NN verification tools while retaining the rigor of dL. This yields infinite-time horizon safety guarantees for neural network control systems.

10. Dec 2024
Revisiting Differential Verification: Equivalence Verification with Confidence

28. Oct 2024
Geometric Path Enumeration for Equivalence Verification of Neural Networks
Geometric Path Enumeration for Equivalence Verification of Neural Networks

We present and evaluate an approach for proving equivalence properties on neural networks and show that the verification of $\epsilon$-equivalence is coNP-complete

21. Dec 2021