[DMANET] CfP—The 8th International Symposium on AI Verification—SAIV 2025 co-located with CAV 2025

CfP—The 8th International Symposium on AI Verification—SAIV 2025
Zagreb, Croatia
July 21–22
co-located with CAV 2025
https://www.aiverification.org/2025/

=== Important Dates (all dates are 11:59 AM UTC) ===

Abstract Submission: April 17 2025
Paper Submission: April 24, 2025
Notification: May 21, 2025

=== SAIV ===

The 8th edition of the International Symposium on AI Verification (SAIV) aims to bring together researchers from the communities on formal methods and artificial intelligence. SAIV 2025 consisted of two workshops that have been merged into a single symposium: FoMLAS and Wolverine. Formal reasoning about learning-based systems raises novel, challenging, and exciting problems, such as the verification of learning-based components, the combination of deep learning and symbolic algorithms, and the data-driven verification of systems. SAIV aims to serve as a platform for idea exchange and cross-pollination on these topics.

SAIV 2025 will host the 6th International Verification of Neural Networks Competition (VNN-COMP'25).

We invite four categories of submissions:



1. *Original papers*: describe original research and sufficient detail to assess the merits and relevance of the submission. For papers reporting experimental results, authors are strongly encouraged to make their data available. We welcome both short and long papers. There are no strict page limits, although we recommend not going below 4 pages and not exceeding 18 pages.
2. *Presentation-only papers*: describe work recently published or submitted. We see this as a way to provide additional access to important developments that the SAIV attendees may be unaware of.
3. *Extended abstracts*: describe preliminary work in progress. These reports may range in length from very short to full papers, and will be judged based on the expected level of interest for the community. ​
4. *(New) This year we also invite benchmark and case-study papers*: showcase practical evaluations, real-world applications, or lessons learned in verifying and deploying safety-critical AI systems, focusing on metrics, methodologies, and safety outcomes.

Papers selected for publications will appear in Springer's LNCS proceedings.

=== Posters ===

We additionally invite attendees to present posters to illustrate published work or research-in-progress. We particularly welcome poster submissions to facilitate interaction during SAIV. Deadline for poster submission: June 20.

=== Topics ===

The topics covered by SAIV include, but are not limited to, the following:

* Safety specifications for systems with AL components

* Symbolic analysis of cyber-physical systems with AI components
* Formal verification of neural networks
* Neuro-symbolic reasoning for AI safety
* Testing approaches for systems with AI components
* Formal guarantees for interpretable AI
* Machine learning for program synthesis and control synthesis
* Machine learning for automated reasoning and theorem-proving
* Differentiable proof certificates
* Statistical approaches to falsification and verification
* Data-driven verification

=== Program Chairs ===

Mirco Giacobbe (University of Birmingham)
Anna Lukina (Delft University of Technology)

**********************************************************
*
* Contributions to be spread via DMANET are submitted to
*
* DMANET@zpr.uni-koeln.de
*
* Replies to a message carried on DMANET should NOT be
* addressed to DMANET but to the original sender. The
* original sender, however, is invited to prepare an
* update of the replies received and to communicate it
* via DMANET.
*
* DISCRETE MATHEMATICS AND ALGORITHMS NETWORK (DMANET)
* http://www.zaik.uni-koeln.de/AFS/publications/dmanet/
*
**********************************************************