CURE is the first multi-norm certified training method that improves union robustness across l_p norms and unseen perturbations on MNIST, CIFAR-10 and TinyImagenet.
Towards stable and efficient training of verifiably robust neural networks
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
verdicts
UNVERDICTED 5representative citing papers
A JAX-based differentiable reachability primitive for continuous- and discrete-time NN dynamics and controllers that supports certified training and sampling-based MPC with gradient refinement.
LightCROWN computes tighter Jacobian bounds for neural networks with smooth nonlinear activations by exploiting their analytical properties, raising verification success rates for neural control barrier functions up to 100% on benchmark control systems.
Certified robustness varies extremely across training seeds with std larger than recent gains, and generalizes poorly to unseen data.
Tutorial introducing applications of the existing α,β-CROWN verifier to scalable formal verification of neural network controllers via bound computation and domain partitioning.
citing papers explorer
-
Towards Generalized Certified Robustness with Multi-Norm Training
CURE is the first multi-norm certified training method that improves union robustness across l_p norms and unseen perturbations on MNIST, CIFAR-10 and TinyImagenet.
-
Parallel Differentiable Reachability for Learning and Planning with Certified Neural Dynamics and Controllers
A JAX-based differentiable reachability primitive for continuous- and discrete-time NN dynamics and controllers that supports certified training and sampling-based MPC with gradient refinement.
-
Efficient Verification of Neural Control Barrier Functions with Smooth Nonlinear Activations
LightCROWN computes tighter Jacobian bounds for neural networks with smooth nonlinear activations by exploiting their analytical properties, raising verification success rates for neural control barrier functions up to 100% on benchmark control systems.
-
On the Extreme Variance of Certified Local Robustness Across Model Seeds
Certified robustness varies extremely across training seeds with std larger than recent gains, and generalizes poorly to unseen data.
-
Bridging Control with Neural Network Verifier alpha-beta-CROWN: A Tutorial
Tutorial introducing applications of the existing α,β-CROWN verifier to scalable formal verification of neural network controllers via bound computation and domain partitioning.