activity
20242026
collaborators

5 papers

cs.LG2026

Flowing Through States: Neural ODE Regularization for Reinforcement Learning

Mohamed Ghanem, Bernd Finkbeiner

Neural networks applied to sequential decision-making tasks typically rely on latent representations of environment states. While environment dynamics dictate how semantic states e…

cs.CR2026

Less Effort, Shorter Proofs: Reinforcement Learning for Security Protocol Analysis in Tamarin

Matthias Cosler, Cas Cremers, Bernd Finkbeiner +2

Tools like Tamarin and ProVerif have achieved notable success in analyzing and verifying complex real-world protocols such as EMV, 5G, and WPA2, even detecting zero-day exploits. D…

cs.LG2026

Natural Synthesis: Outperforming Reactive Synthesis Tools with Large Reasoning Models

Frederik Schmitt, Matthias Cosler, Niklas Metzger +4

Reactive synthesis, the problem of automatically constructing a hardware circuit from a logical specification, is a long-standing challenge in formal verification. It is elusive fo…

cs.LG2025

Learning Representations Through Contrastive Neural Model Checking

Vladimir Krsmanovic, Matthias Cosler, Mohamed Ghanem +1

Model checking is a key technique for verifying safety-critical systems against formal specifications, where recent applications of deep learning have shown promise. However, while…

cs.LG2024

Learning Better Representations From Less Data For Propositional Satisfiability

Mohamed Ghanem, Frederik Schmitt, Julian Siber +1

Training neural networks on NP-complete problems typically demands very large amounts of training data and often needs to be coupled with computationally expensive symbolic verifie…