Safety Verification for Neural Networks Based on Set-boundary Analysis

TL;DR

This paper introduces a set-boundary analysis method for safety verification of neural networks, leveraging topological properties to efficiently determine if network outputs stay within safe bounds, especially for invertible NNs.

Contribution

The paper proposes a novel set-boundary reachability approach utilizing the homeomorphism property of certain neural networks to improve safety verification efficiency.

Findings

Effective in verifying safety of invertible neural networks.

Reduces computational burden by focusing on input set boundaries.

Demonstrated success on example networks.

Abstract

Neural networks (NNs) are increasingly applied in safety-critical systems such as autonomous vehicles. However, they are fragile and are often ill-behaved. Consequently, their behaviors should undergo rigorous guarantees before deployment in practice. In this paper we propose a set-boundary reachability method to investigate the safety verification problem of NNs from a topological perspective. Given an NN with an input set and a safe set, the safety verification problem is to determine whether all outputs of the NN resulting from the input set fall within the safe set. In our method, the homeomorphism property of NNs is mainly exploited, which establishes a relationship mapping boundaries to boundaries. The exploitation of this property facilitates reachability computations via extracting subsets of the input set rather than the entire input set, thus controlling the wrapping effect in reachability analysis and facilitating the reduction of computation burdens for safety verification. The homeomorphism property exists in some widely used NNs such as invertible NNs. Notable representations are invertible residual networks (i-ResNets) and Neural ordinary differential equations (Neural ODEs). For these NNs, our set-boundary reachability method only needs to perform reachability analysis on the boundary of the input set. For NNs which do not feature this property with respect to the input set, we explore subsets of the input set for establishing the local homeomorphism property, and then abandon these subsets for reachability computations. Finally, some examples demonstrate the performance of the proposed method.