General Cutting Planes for Bound-Propagation-Based Neural Network Verification. (arXiv:2208.05740v1 [cs.LG])

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, robustness, and safety. However, existing works cannot
handle the general form of cutting plane constraints widely accepted in
traditional solvers, which are crucial for strengthening verifiers with
tightened convex relaxations. In this paper, we generalize the bound
propagation procedure to allow the addition of arbitrary cutting plane
constraints, including those involving relaxed integer variables …

general lg network neural network planes verification