10 citations · 17 across the 9 of their papers we have counts for
5 papers · 1 filter
TESTNAV: Pareto-Guided Search for Compositional Robustness Testing
Arooj Arif, Tobias Hartung, Elena Botoeva +1
Deep learning models remain vulnerable to real-world input perturbations, especially when multiple corruptions co-occur in the same input (e.g., brightness shifts and motion blur).…
TestifAI: Tomography-Based Testing for Deep Learning Systems
Arooj Arif, Tobias Hartung, Elena Botoeva +1
As AI systems are increasingly deployed in safety-critical application domains (e.g., autonomous driving), associated risks increase too. Deep learning models underlying modern AI…
Query Inseparability for ALC Ontologies
Elena Botoeva, Carsten Lutz, Vladislav Ryzhikov +2
We investigate the problem whether two ALC ontologies are indistinguishable (or inseparable) by means of queries in a given signature, which is fundamental for ontology engineering…
Inseparability and Conservative Extensions of Description Logic Ontologies: A Survey
Elena Botoeva, Boris Konev, Carsten Lutz +3
The question whether an ontology can safely be replaced by another, possibly simpler, one is fundamental for many ontology engineering and maintenance tasks. It underpins, for exam…
Beyond OWL 2 QL in OBDA: Rewritings and Approximations (Extended Version)
Elena Botoeva, Diego Calvanese, Valerio Santarelli +3
Ontology-based data access (OBDA) is a novel paradigm facilitating access to relational data, realized by linking data sources to an ontology by means of declarative mappings. DL-L…