2 citations · 3 across the 3 of their papers we have counts for
3 papers
Monitizer: Automating Design and Evaluation of Neural Network Monitors
Muqsit Azeem, Marta Grobelna, Sudeep Kanav +3
The behavior of neural networks (NNs) on previously unseen types of data (out-of-distribution or OOD) is typically unpredictable. This can be dangerous if the network's output is u…
Guessing Winning Policies in LTL Synthesis by Semantic Learning
Jan Kretinsky, Tobias Meggendorfer, Maximilian Prokop +1
We provide a learning-based technique for guessing a winning strategy in a parity game originating from an LTL synthesis problem. A cheaply obtained guess can be useful in several…
Runtime Monitoring for Out-of-Distribution Detection in Object Detection Neural Networks
Vahid Hashemi, Jan Křetínsky, Sabine Rieder +1
Runtime monitoring provides a more realistic and applicable alternative to verification in the setting of real neural networks used in industry. It is particularly useful for detec…