most citedThe 6th International Verification of Neural Networks Competition (VNN-COMP 2025): Summary and Results

4 citations · 4 across the 4 of their papers we have counts for

collaborators

7 papers

eess.SY2026

Set-Based Training of Neural Barrier Certificates for Safety Verification of Dynamical Systems

Miriam Kranzlmüller, Lukas Koller, Tobias Ladner +1

Barrier certificates are scalar functions over the state space of dynamical systems that separate all unsafe states from all reachable states. The existence of a barrier certificat…

cs.LG2026

Provably Explaining Neural Additive Models

Shahaf Bassan, Yizhak Yisrael Elboher, Tobias Ladner +4

Despite significant progress in post-hoc explanation methods for neural networks, many remain heuristic and lack provable guarantees. A key approach for obtaining explanations with…

cs.LG20254 cited

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…

cs.LO2025

Abstraction-Based Proof Production in Formal Verification of Neural Networks

Yizhak Yisrael Elboher, Omri Isac, Guy Katz +2

Modern verification tools for deep neural networks (DNNs) increasingly rely on abstraction to scale to realistic architectures. In parallel, proof production is becoming a critical…

cs.LG2025

Explaining, Fast and Slow: Abstraction and Refinement of Provable Explanations

Shahaf Bassan, Yizhak Yisrael Elboher, Tobias Ladner +2

Despite significant advancements in post-hoc explainability techniques for neural networks, many current methods rely on heuristics and do not provide formally provable guarantees…

cs.LG2025

Out of the Shadows: Exploring a Latent Space for Neural Network Verification

Lukas Koller, Tobias Ladner, Matthias Althoff

Neural networks are ubiquitous. However, they are often sensitive to small input changes. Hence, to prevent unexpected behavior in safety-critical applications, their formal verifi…