Call for Papers

We invite participants from all disciplines related to formal verification and machine learning-based systems, including but not limited to machine learning, computer-aided verification, programming languages, robotics and control, cyber security, and optimization. We invite any submissions surrounding formal verification for machine learning systems and machine learning for formal verification, including but not limited to:

• Formal verification methods for machine learning models, such as neural networks (NNs), tree-based models, Gaussian process, and nonparametric models;

• Algorithms for verifying novel or unconventional specifications, especially those that arise in new applications of verified machine learning;

• Scaling formal verification algorithms for machine learning or via machine learning;

• Novel training procedures that produce high-assurance models amenable to formal verification;

• New applications for formal verification in fields such as robotics, control, aeronautics, computer security, and computer systems;

• Surveys on the trade-offs between verifiable guarantees, model performance, and model applicability;

• Design of representative and generic benchmarks and datasets for formal verification of machine learning and machine learning for formal verification;

• Development of user-friendly toolkits for machine learning and verification practitioners.

Reviewing will be performed in double-blind, with criteria including:

• Quality of the methodology and experiments

• Novelty

• Relevance

• Soundness

• Societal impacts

Author Instructions

Submission Deadline: TBD AoE on CMT

Submission Link: TBD

Submission Format: Submitted papers are recommended to have at most 4 pages with unlimited bibliography and appendix, using the WFVML 2024 LaTeX style files. While the page limit is not hard, a concise presentation can greatly improve readability. Submissions must be anonymous following ICML requirements and ethics standards.  Accepted papers will be hosted on this workshop website but are considered non-archival and can be submitted to other workshops, conferences, or journals, subject to their submission policies. 

Dual submission policy: We allow dual submission with other workshops and conferences as well submissions with large overlap to your recently published papers. In these cases, we particularly encourage the submission of a more concise version.

Author Notification: TBD

Camera Ready: TBD AoE on CMT

Best Paper Award🏆: To encourage high-quality submissions, we plan to offer a best paper award (details TBA).

Contact: For technical problems regarding submission, please contact TBD.