18 citations · 100 across the 22 of their papers we have counts for
4 papers · 1 filter
Verifying And Interpreting Neural Networks using Finite Automata
Marco Sälzer, Eric Alsmann, Florian Bruse +1
Verifying properties and interpreting the behaviour of deep neural networks (DNN) is an important task given their ubiquitous use in applications, including safety-critical ones, a…
Capturing Bisimulation-Invariant Exponential-Time Complexity Classes
Florian Bruse, David Kronenberger, Martin Lange
Otto's Theorem characterises the bisimulation-invariant PTIME queries over graphs as exactly those that can be formulated in the polyadic mu-calculus, hinging on the Immerman-Vardi…
Fundamental Limits in Formal Verification of Message-Passing Neural Networks
Marco Sälzer, Martin Lange
Output reachability and adversarial robustness are among the most relevant safety properties of neural networks. We show that in the context of Message Passing Neural Networks (MPN…
Reachability In Simple Neural Networks
Marco Sälzer, Martin Lange
We investigate the complexity of the reachability problem for (deep) neural networks: does it compute valid output given some valid input? It was recently claimed that the problem…