There are 1 repository under neural-network-verification topic.
alpha-beta-CROWN: An Efficient, Scalable and GPU Accelerated Neural Network Verifier (winner of VNN-COMP 2021, 2022, and 2023)
Neural Network Verification Software Tool
DIG is a numerical invariant generation tool. It infers program invariants or properties over (i) program execution traces or (ii) program source code. DIG supports many forms of numerical invariants, including nonlinear equalities, octagonal and interval properties, min/max-plus relations, and congruence relations.
Verification of neural networks based on input splitting and forward propagation of symbolic intervals with fresh variables.
Uses the simplex to propose a tighter boundary for the l1 perturbation of the convex activation function network, improving the effect of the CROWN algorithm.