[PDF][PDF] Beta-crown: Efficient bound propagation with per-neuron split constraints for neural network robustness verification

S Wang, H Zhang, K Xu, X Lin, S Jana… - Advances in neural …, 2021 - proceedings.neurips.cc
Bound propagation based incomplete neural network verifiers such as CROWN are very
efficient and can significantly accelerate branch-and-bound (BaB) based complete …

General cutting planes for bound-propagation-based neural network verification

H Zhang, S Wang, K Xu, L Li, B Li… - Advances in neural …, 2022 - proceedings.neurips.cc
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 …

Verifying controllers with vision-based perception using safe approximate abstractions

C Hsieh, Y Li, D Sun, K Joshi… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Fully formal verification of perception models is likely to remain challenging in the
foreseeable future, and yet these models are being integrated into safety-critical control …

Conformal prediction for stl runtime verification

L Lindemann, X Qin, JV Deshmukh… - Proceedings of the ACM …, 2023 - dl.acm.org
We are interested in predicting failures of cyber-physical systems during their operation.
Particularly, we consider stochastic systems and signal temporal logic specifications, and we …

Perception contracts for safety of ML-enabled systems

A Astorga, C Hsieh, P Madhusudan… - Proceedings of the ACM on …, 2023 - dl.acm.org
We introduce a novel notion of perception contracts to reason about the safety of controllers
that interact with an environment using neural perception. Perception contracts capture …