Stefan Leue
YOU?
Author Swipe
View article: Stable Robot Motions on Manifolds: Learning Lyapunov-Constrained Neural Manifold ODEs
Stable Robot Motions on Manifolds: Learning Lyapunov-Constrained Neural Manifold ODEs Open
Learning stable dynamical systems from data is crucial for safe and reliable robot motion planning and control. However, extending stability guarantees to trajectories defined on Riemannian manifolds poses significant challenges due to the…
View article: Automated consistency analysis for legal contracts
Automated consistency analysis for legal contracts Open
Business contracts, particularly sale and purchase agreements, often contain a large number of clauses and are correspondingly long and complex. In practice, it is therefore a great challenge to keep track of their legal context and to ide…
View article: Reproducibility Package: Solving Probabilistic Verification problems of Neural Networks using Branch and Bound
Reproducibility Package: Solving Probabilistic Verification problems of Neural Networks using Branch and Bound Open
This is a reproducibility package for the paper "Solving Probabilistic Verification Problems of Neural Networks using Branch and Bound" by David Boetius, Stefan Leue, and Tobias Sutter, published at ICML 2025. It contains: source code used…
View article: Automated Consistency Analysis for Legal Contracts
Automated Consistency Analysis for Legal Contracts Open
Business contracts, particularly sale and purchase agreements, often contain a large number of clauses and are correspondingly long and complex. In practice, it is therefore a great challenge to keep track of their legal context and to ide…
View article: Counterexample-Guided Repair of Reinforcement Learning Systems Using Safety Critics
Counterexample-Guided Repair of Reinforcement Learning Systems Using Safety Critics Open
Naively trained Deep Reinforcement Learning agents may fail to satisfy vital safety constraints. To avoid costly retraining, we may desire to repair a previously trained reinforcement learning agent to obviate unsafe behaviour. We devise a…
View article: Verifying Global Neural Network Specifications using Hyperproperties
Verifying Global Neural Network Specifications using Hyperproperties Open
Current approaches to neural network verification focus on specifications that target small regions around known input data points, such as local robustness. Thus, using these approaches, we can not obtain guarantees for inputs that are no…
View article: Verifying Global Neural Network Specifications using Hyperproperties
Verifying Global Neural Network Specifications using Hyperproperties Open
Current approaches to neural network verification focus on specifications that target small regions around known input data points, such as local robustness. Thus, using these approaches, we can not obtain guarantees for inputs that are no…
View article: A Robust Optimisation Perspective on Counterexample-Guided Repair of Neural Networks: Experimental Data
A Robust Optimisation Perspective on Counterexample-Guided Repair of Neural Networks: Experimental Data Open
Full experimental data for the paper "A Robust Optimisation Perspective on Counterexample-Guided Repair of Neural Networks". We also include a virtual machine for reproducing our experiments.
View article: Formal Modeling and Analysis of Legal Contracts using ContractCheck
Formal Modeling and Analysis of Legal Contracts using ContractCheck Open
We describe a method and tool called \textit{ContractCheck} that allows for the consistency analysis of legal contracts, in particular Sales Purchase Agreements (SPAs). The analysis relies on an encoding of the premises for the execution o…
View article: symQV: Automated Symbolic Verification of Quantum Programs
symQV: Automated Symbolic Verification of Quantum Programs Open
We present symQV, a symbolic execution framework for writing and verifying quantum computations in the quantum circuit model. symQV can automatically verify that a quantum program complies with a first-order specification. We formally intr…
View article: Automated repair for timed systems
Automated repair for timed systems Open
We present algorithms and techniques for the repair of timed system models, given as networks of timed automata (NTA). The repair is based on an analysis of timed diagnostic traces (TDTs) that are computed by real-time model checking tools…
View article: SpecAttack: Specification-Based Adversarial Training for Deep Neural Networks.
SpecAttack: Specification-Based Adversarial Training for Deep Neural Networks. Open
Safety specification-based adversarial training aims to generate examples violating a formal safety specification and therefore provides approaches for repair. The need for maintaining high prediction accuracy while ensuring the save behav…
View article: DeepOpt: Scalable Specification-based Falsification of Neural Networks using Black-Box Optimization.
DeepOpt: Scalable Specification-based Falsification of Neural Networks using Black-Box Optimization. Open
Decisions made by deep neural networks (DNNs) have a tremendous impact on the dependability of the systems that they are embedded into, which is of particular concern in the realm of safety-critical systems. In this paper we consider speci…
View article: TarTar: A Timed Automata Repair Tool
TarTar: A Timed Automata Repair Tool Open
We present TarTar, an automatic repair analysis tool that, given a timed diagnostic trace (TDT) obtained during the model checking of a timed automaton model, suggests possible syntactic repairs of the analyzed model. The suggested repairs…
View article: Correctness of an ATL Model Transformation from SysML State Machine Diagrams to Promela
Correctness of an ATL Model Transformation from SysML State Machine Diagrams to Promela Open
In this paper we discuss the correctness of an ATL-based model transformation from the systems engineering modelling language SysML into Promela, the input language of the SPIN model checker.More precisely, we reduce showing the correctnes…
View article: Clock Bound Repair for Timed Systems
Clock Bound Repair for Timed Systems Open
We present algorithms and techniques for the repair of timed system models, given as networks of timed automata (NTA). The repair is based on an analysis of timed diagnostic traces (TDTs) that are computed by real-time model checking tools…
View article: Extending Non-Termination Proof Techniques to Asynchronously Communicating Concurrent Programs
Extending Non-Termination Proof Techniques to Asynchronously Communicating Concurrent Programs Open
Currently, there are no approaches known that allow for non-termination proofs of concurrent programs which account for asynchronous communication via FIFO message queues. Those programs may be written in high-level languages such as Java …
View article: Automated Invariant Generation for the Verification of Real-Time Systems
Automated Invariant Generation for the Verification of Real-Time Systems Open
We present an approach to automatically generating invariants for timed automata models. The CIPM algorithm that we propose first computes new invariants for timed automata control locations taking their originally defined invariants as we…
View article: Proceedings 2nd International Workshop on Causal Reasoning for Embedded\n and safety-critical Systems Technologies
Proceedings 2nd International Workshop on Causal Reasoning for Embedded\n and safety-critical Systems Technologies Open
The second international CREST workshop continued the focus of the first\nCREST workshop: addressing approaches to causal reasoning in engineering\ncomplex embedded and safety-critical systems. Relevant approaches to causal\nreasoning have…
View article: Automated Freedom from Interference Analysis for Automotive Software
Automated Freedom from Interference Analysis for Automotive Software Open
Freedom from Interference for automotive software systems developed according to the ISO 26262 standard means that a fault in a less safety critical software component will not lead to a fault in a more safety critical component. It is an …
View article: (De-)Composing Causality in Labeled Transition Systems
(De-)Composing Causality in Labeled Transition Systems Open
In this paper we introduce a notion of counterfactual causality in the Halpern and Pearl sense that is compositional with respect to the interleaving of transition systems. The formal framework for reasoning on what caused the violation of…