5th Workshop on
Artificial Intelligence and
fOrmal VERification, Logic,
Automata, and sYnthesis

The increasing adoption of Artificial Intelligence techniques in safety-critical systems, employed in real world scenarios, requires the design of reliable, robust, and verifiable methodologies. Artificial Intelligence systems employed in such applications need to provide formal guarantees about their safety, increasing the need for a close interaction between the Artificial Intelligence and Formal Methods scientific communities, and possibly leading to the proposal of novel neurosymbolic approaches.

To witness this increasing need, tools and methodologies integrating Formal Methods and Artificial Intelligence, and more broadly symbolic and sub-symbolic solutions, are getting more and more attention, especially considering the wide-range and pervasive applications of machine and deep learning models.

The workshop is the main official initiative supported by the OVERLAY group. The event aims at establishing a stable, long-term scientific forum on relevant topics connected to the relationships between Artificial Intelligence and Formal Methods, by providing a stimulating environment where researchers can discuss about opportunities and challenges at the border of the two areas.

Important goals of the workshop are (i) to encourage the ongoing interaction between the formal methods and artificial intelligence communities, (ii) to identify innovative tools and methodologies, and (iii) to elicit a discussion on open issues and new challenges.

This year edition will be held on November 7th, 2023, as a workshop co-located with AIxIA 2023, which is scheduled to be held in Rome, Italy.

Participants must be registered to AIxIA 2023. Overlay does not have an additional specific fee.

Invited speaker

Luciano Serafini

Fondazione Bruno Kessler, Trento,Italy

Title
NeuroSymbolic AI: between probability and fuzzyness

Abstract
Neurosymbolic AI (NeSy) aims to integrate logic-based knowledge representation and reasoning with neural networks. Numerous approaches to NeSy are being developed, and I believe they can be categorized into two main groups, depending on how the quantitative predictions of a neural network are interpreted in the logic. The two main classes are based on fuzzy logic and probabilistic logic. Two representative witnesses of these classes are Logic Tensor Networks (LTN) and DeepProblog. In this presentation, I will provide descriptions of LTN and DeepProblog, and I will attempt to compare the two systems, highlighting their similarities and differences.

Call for contributions

We accept extended abstracts (4 pages + references) focusing on the interaction between Artificial Intelligence and Formal Methods and on the issue of symbolic/sub-symbolic integration. Invited talks will complement the presentations of contributed papers.

Topics of interest include (but are not limited to):

• automata theory
• automated reasoning
• automated planning and scheduling
• controller synthesis
• formal specification languages
• formal verification
• game theory
• hybrid and discrete systems
• logics in computer science
• neurosymbolic approaches
• logics for neural networks
• neural networks for logic
• reactive synthesis
• runtime verification and monitoring
• satisfiability modulo theories and theorem proving
• specification and verification of machine/deep learning systems
• tools and applications

Contributed papers can present recent results at the border of the two fields, new research directions, challenges and perspectives. Presentation of results recently published in other scientific journals or conferences is also welcome.

We plan to include all papers in the Proceedings of the event, published at CEUR Workshop Proceedings . CEUR WS proceedings are archival proceedings indexed by DBLP and Scopus.

Submissions

Submitted papers should not exceed four (4) pages plus references. Authors are asked to use the Overlay-specific CEURART LaTeX style, which is available here.

Submissions must be in PDF format and will be handled via the EasyChair Conference system at the following address: https://easychair.org/conferences/?conf=overlay2023 .

Registration and participation fees

OVERLAY 2023 will take place as part of AIxIA 2023. As a consequence, participants to the workshop must be registered to AIxIA. The registration to the main conference gives access to all the workshops including OVERLAY.

See the main conference web site for information on registration fees and cutoff dates.

Program Committee

Chairs

• Andrea Brunello • University of Udine, Italy
• Alessandro Gianola • INESC-ID / Instituto Superior Técnico, Lisbon, Portugal
• Fabio Mogavero • University of Napoli Federico II, Italy

PC Members

• Dylan Bellier • University of Rennes, France
• Massimo Benerecetti • University of Napoli Federico II, Italy
• Laura Bozzelli • University of Napoli Federico II, Italy
• Dario Della Monica • University of Udine, Italy
• Daniele Dell'Erba • University of Liverpool, UK
• Marco Faella • University of Napoli Federico II, Italy
• Luca Geatti • University of Udine, Italy
• Silvio Ghilardi • University of Milan, Italy
• Nicola Gigante • Free University of Bozen-Bolzano, Italy
• Inês Lynce • INESC-ID / Instituto Superior Técnico, Lisbon, Portugal
• Andrea Mazzullo • University of Trento, Italy
• Andrea Micheli • Fondazione Bruno Kessler, Trento, Italy
• AndreA Orlandini • ISTC-CNR, Rome, Italy
• Matteo Papini • Universitat Pompeu Fabra, Barcelona, Spain
• Gian Luca Pozzato • University of Turin, Italy
• Guido Sciavicco • University of Ferrara, Italy
• Nicola Saccomanno • University of Udine, Italy
• Ionel Eduard Stan • Free University of Bozen-Bolzano, Italy
• Cesare Tinelli • The University of Iowa, USA
• Tiziano Villa • University of Verona, Italy
• Zavatteri Matteo • University of Padova, Italy

Contacts

For more information email to overlay2023@easychair.org.