General cutting planes for bound-propagation-based neural network verification
Bound propagation methods, when combined with branch and bound, are among the most
effective methods to formally verify properties of deep neural networks such as correctness …
effective methods to formally verify properties of deep neural networks such as correctness …
Beta-crown: Efficient bound propagation with per-neuron split constraints for neural network robustness verification
Bound propagation based incomplete neural network verifiers such as CROWN are very
efficient and can significantly accelerate branch-and-bound (BaB) based complete …
efficient and can significantly accelerate branch-and-bound (BaB) based complete …
First three years of the international verification of neural networks competition (VNN-COMP)
This paper presents a summary and meta-analysis of the first three iterations of the annual
International Verification of Neural Networks Competition (VNN-COMP), held in 2020, 2021 …
International Verification of Neural Networks Competition (VNN-COMP), held in 2020, 2021 …
Sok: Certified robustness for deep neural networks
Great advances in deep neural networks (DNNs) have led to state-of-the-art performance on
a wide range of tasks. However, recent studies have shown that DNNs are vulnerable to …
a wide range of tasks. However, recent studies have shown that DNNs are vulnerable to …
The second international verification of neural networks competition (vnn-comp 2021): Summary and results
This report summarizes the second International Verification of Neural Networks
Competition (VNN-COMP 2021), held as a part of the 4th Workshop on Formal Methods for …
Competition (VNN-COMP 2021), held as a part of the 4th Workshop on Formal Methods for …
Training certifiably robust neural networks with efficient local lipschitz bounds
Certified robustness is a desirable property for deep neural networks in safety-critical
applications, and popular training algorithms can certify robustness of a neural network by …
applications, and popular training algorithms can certify robustness of a neural network by …
Efficiently computing local lipschitz constants of neural networks via bound propagation
Lipschitz constants are connected to many properties of neural networks, such as
robustness, fairness, and generalization. Existing methods for computing Lipschitz constants …
robustness, fairness, and generalization. Existing methods for computing Lipschitz constants …
PRIMA: general and precise neural network certification via scalable convex hull approximations
Formal verification of neural networks is critical for their safe adoption in real-world
applications. However, designing a precise and scalable verifier which can handle different …
applications. However, designing a precise and scalable verifier which can handle different …
The third international verification of neural networks competition (VNN-COMP 2022): Summary and results
This report summarizes the 3rd International Verification of Neural Networks Competition
(VNN-COMP 2022), held as a part of the 5th Workshop on Formal Methods for ML-Enabled …
(VNN-COMP 2022), held as a part of the 5th Workshop on Formal Methods for ML-Enabled …
Complete verification via multi-neuron relaxation guided branch-and-bound
State-of-the-art neural network verifiers are fundamentally based on one of two paradigms:
either encoding the whole verification problem via tight multi-neuron convex relaxations or …
either encoding the whole verification problem via tight multi-neuron convex relaxations or …