arXiv subjects

Kristóf Marussy

Publications and source records attributed to Kristóf Marussy.

4 recordsLinked to original sources

arXiv2025

Certifying Robustness of Graph Convolutional Networks for Node Perturbation with Polyhedra Abstract Interpretation

Graph convolutional neural networks (GCNs) are powerful tools for learning graph-based knowledge representations from training data. However, they are vulnerable to small perturbations in the input graph, which makes them susceptible to input faults or adversarial attacks. This poses a significant problem for GCNs intended to be used in critical applications, which need to provide certifiably robust services even in the presence of adversarial perturbations. We propose an improved GCN robustness certification technique for node classification in the presence of node feature perturbations. We introduce a novel polyhedra-based abstract interpretation approach to tackle specific challenges of graph data and provide tight upper and lower bounds for the robustness of the GCN. Experiments show that our approach simultaneously improves the tightness of robustness bounds as well as the runtime performance of certification. Moreover, our method can be used during training to further improve the robustness of GCNs.

cs.LG↗

arXiv2024

A Lazy Abstraction Algorithm for Markov Decision Processes: Theory and Initial Evaluation

Analysis of Markov Decision Processes (MDP) is often hindered by state space explosion. Abstraction is a well-established technique in model checking to mitigate this issue. This paper presents a novel lazy abstraction method for MDP analysis based on adaptive simulation graphs. Refinement is performed only when new parts of the state space are explored, which makes partial exploration techniques like Bounded Real-Time Dynamic Programming (BRTDP) retain more merged states. Therefore, we propose a combination of lazy abstraction and BRTDP. To evaluate the performance of our algorithm, we conduct initial experiments using the Quantitative Verification Benchmark Set.

cs.LO↗

arXiv2021

Worst-Case Execution Time Calculation for Query-Based Monitors by Witness Generation

Runtime monitoring plays a key role in the assurance of modern intelligent cyber-physical systems, which are frequently data-intensive and safety-critical. While graph queries can serve as an expressive yet formally precise specification language to capture the safety properties of interest, there are no timeliness guarantees for such auto-generated runtime monitoring programs, which prevents their use in a real-time setting. While worst-case execution time (WCET) bounds derived by existing static WCET estimation techniques are safe, they may not be tight as they are unable to exploit domain-specific (semantic) information about the input models. This paper presents a semantic-aware WCET analysis method for data-driven monitoring programs derived from graph queries. The method incorporates results obtained from low-level timing analysis into the objective function of a modern graph solver. This allows the systematic generation of input graph models up to a specified size (referred to as witness models) for which the monitor is expected to take the most time to complete. Hence the estimated execution time of the monitors on these graphs can be considered as safe and tight WCET. Additionally, we perform a set of experiments with query-based programs running on a real-time platform over a set of generated models to investigate the relationship between execution times and their estimates, and compare WCET estimates produced by our approach with results from two well-known timing analyzers, aiT and OTAWA.

cs.SE↗

arXiv2020

Simulation-based Safety Assessment of High-level Reliability Models

Systems engineering approaches use high-level models to capture the architecture and behavior of the system. However, when safety engineers conduct safety and reliability analysis, they have to create formal models, such as fault-trees, according to the behavior described by the high-level engineering models and environmental/fault assumptions. Instead of creating low-level analysis models, our approach builds on engineering models in safety analysis by exploiting the simulation capabilities of recent probabilistic programming and simulation advancements. Thus, it could be applied in accordance with standards and best practices for the analysis of a critical automotive system as part of an industrial collaboration, while leveraging high-level block diagrams and statechart models created by engineers. We demonstrate the applicability of our approach in a case study adapted from the automotive system from the collaboration.

cs.SE↗