April 2nd, 2020 
Daniela Lopez de Luise VNN20 Call for Papers and Benchmarks
The 2020 Workshop on Verification of Neural Networks (VNN20) will be held on July 19, 2020 in Los Angeles, USA, collocated with the 32nd International Conference on Computer-Aided Verification (CAV 2020). It aims to bring together researchers interested in methods and tools providing guarantees about the behaviours of neural networks and systems built from them. Given the COVID-19 situation, the workshop is anticipated to be conducted remotely. The workshop will also present the results of the Verification of Neural Networks Competition (VNN-COMP) being conducted asynchronously ongoingly.
VNN Website: https://sites.google.com/view/vnn20/
We will consider three types of submissions: benchmarks, previously published results, and novel contributions. Each submission must be clearly identified as belonging to one of these categories. For benchmarks, we expect artifacts such as model files to be made available. Accepted submissions will be invited for oral presentation or poster presentation.
Paper format and submission:
For novel contributions, authors are invited to submit 2-4 page short papers. For previously published papers, authors may submit the previously published paper. Submissions are accepted through Easychair:
Subject to any copyright restriction, we aim to collect the accepted abstracts/papers as informal proceedings to be made available after the workshop and on the workshop web page. We will consider a special issue in a journal or a conference post-proceedings should there be sufficient interest.
Key Dates:
June 1, 2020: submission deadline
June 22, 2020: notification of acceptance
July 19, 2020: VNN20 workshop
Topics of Interests:
The topics covered by the workshop include, but are not limited to, the following:
* Formal specifications for neural networks and systems based on them;
* Neural network verification benchmarks;
* SAT-based and SMT-based methods for the verification of machine learning systems;
* Mixed-integer Linear Programming methods for the verification of neural networks;
* Testing approaches to neural networks;
* Optimisation-based methods for the verification of neural networks;
* Statistical approaches to the verification of neural networks.
Organizers:
Posted in