6 papers
Quantitative Linear Logic for Neuro-Symbolic Learning and Verification
Thomas Flinkow, Ekaterina Komendantskaya, Matteo Capucci +1
Differentiable Logics are deployed in neuro-symbolic learning tasks as a way of embedding logical constraints in the training objective of neural networks. A differentiable logic c…
The 6th International Verification of Neural Networks Competition (VNN-COMP 2025): Summary and Results
Konstantin Kaulen, Tobias Ladner, Stanley Bak +8
This report summarizes the 6th International Verification of Neural Networks Competition (VNN-COMP 2025), held as a part of the 8th International Symposium on AI Verification (SAIV…
A General Framework for Property-Driven Machine Learning
Thomas Flinkow, Marco Casadio, Colin Kessler +2
Neural networks have been shown to frequently fail to learn critical safety and correctness properties purely from data, highlighting the need for training methods that directly in…
Neural Network Verification for Gliding Drone Control: A Case Study
Colin Kessler, Ekaterina Komendantskaya, Marco Casadio +5
As machine learning is increasingly deployed in autonomous systems, verification of neural network controllers is becoming an active research domain. Existing tools and annual veri…
Comparing differentiable logics for learning with logical constraints
Thomas Flinkow, Barak A. Pearlmutter, Rosemary Monahan
Extensive research on formal verification of machine learning systems indicates that learning from data alone often fails to capture underlying background knowledge, such as specif…
Creating a Formally Verified Neural Network for Autonomous Navigation: An Experience Report
Syed Ali Asadullah Bukhari, Thomas Flinkow, Medet Inkarbekov +2
The increased reliance of self-driving vehicles on neural networks opens up the challenge of their verification. In this paper we present an experience report, describing a case st…