Poster
Important dates
Call for papers
Neural networks power critical applications, from autonomous vehicles
to medical diagnostics, but their opacity pose significant safety and
trust challenges. Formal logical frameworks offer a rigorous path to
understand, validate, and trust these models. This workshop aims to
bridge the gap between logic and neural network analysis.
We invite contributions that demonstrate how logical frameworks can
address core challenges in neural‑network analysis. Topics of interest
include the expressivity of logical formalisms for neural networks, the
formal verification of safety‑critical properties, the development of
interpretation mechanisms grounded in logic, and the assessment of the
computational complexity of model behavior.
- Expressivity and Translation: Can logical formalisms accurately
represent neural network behavior? We seek submissions exploring
translation of neural architectures (CNNs, GNNs, RNNs, transformers)
into logical specifications or vice versa.
- Safety Verification: Can logic provide formal guarantees of neuron
networks safety-critical properties?
- Logical Interpretation: Can logic help building human-understandable
explanations grounded in logic?
- Decidability and Computational Complexity: Can logic help answer
foundational questions about the tractability of neural network
analysis?
Submissions
Submissions can be in three categories:
- Regular paper: at least 10 pages + bibliography
- Short paper: 5-9 pages + bibliography
- Abstract of already published paper: 1-3 pages + bibliography
Submissions should follow the CEURART format. The templare is
available here: http://ceur-ws.org/Vol-XXX/CEURART.zip.
The proceedings shall be submitted to CEUR-WS.org for online
publication. Authors of regular and short papers may opt out of having
their work included in the proceedings. Abstracts of already published
papers will not be included in the proceedings. We plan to evaluate the
possibility of a journal special issue, depending on the outcome of the
workshop.
Invited speaker
Martin Grohe, RWTH Aachen University, Germany webpage
Invited tutorial speaker
Omri Isac, Hebrew University of Jerusalem, Israël webpage, Verification of
DNNs with Marabou
PC members
- Bartosz Bednarczyk, University of Wrocław & TU Wien, Poland
& Austria
- Isabelle Bloch, Sorbonne Université, France
- Thomas Bolander, DTU Copenhagen, Denmark
- Elena Botoeva, University of Kent, UK
- Roberto Confalonieri, University of Padua, Italy
- David Tena Cucala, University of Oxford, UK
- Stephane Demri, CNRS, Ecole Normale Supérieure de Paris-Saclay,
France
- Avijeet Ghosh, ENS de Lyon, France
- Oliver Kutz, Free University of Bozen-Bolzano, Italy
- Antti Kuusisto, Tampere University, Finland
- Luis Lamb, Federal University of Rio Grande do Sul, Brazil
- Martin Lange, University of Kassel, Germany
- Mena Leemhuis, Free University of Bozen-Bolzano, Italy
- Alessio Lomuscio, Imperial College London, UK
- Carsten Lutz, University of Leipzig, Germany
- Marc Plantevit, EPITA, Lyon, France
- Franco Raimondi, Gran Sasso Science Institute, Italy
- Céline Robardet, INSA Lyon
- Przemysław A. Wałęga, Queen Mary University of London, UK
Organization
- Marco Sälzer, RPTU University of Kaiserslautern-Landau, Germany
- François Schwarzentruber, Ecole Normale Supérieure de Lyon,
France
- Nicolas Troquard, Gran Sasso Science Institute, L’Aquila, Italy