Output Reachable Set Estimation and Verification for Multi-Layer Neural Networks

Abstract

In this paper, the output reachable estimation and safety verification problems for multi-layer perceptron neural networks are addressed. First, a conception called maximum sensitivity in introduced and, for a class of multi-layer perceptrons whose activation functions are monotonic functions, the maximum sensitivity can be computed via solving convex optimization problems. Then, using a simulation-based method, the output reachable set estimation problem for neural networks is formulated into a chain of optimization problems. Finally, an automated safety verification is developed based on the output reachable set estimation result. An application to the safety verification for a robotic arm model with two joints is presented to show the effectiveness of proposed approaches.

8 pages, 9 figures, to appear in TNNLS

References in corpus (2)

• Deep Learning in Neural Networks: An Overview
• End to End Learning for Self-Driving Cars

Cited by in corpus (9)

• Testing Deep Neural Networks
• Reachable Set Computation and Safety Verification for Neural Networks with ReLU Activations
• Branch and Bound for Piecewise Linear Neural Network Verification
• Reachability Analysis of Deep Neural Networks with Provable Guarantees
• Neural State Classification for Hybrid Systems
• Reachable Set Estimation and Safety Verification for Piecewise Linear Systems with Neural Network Controllers
• ReLUSyn: Synthesizing Stealthy Attacks for Deep Neural Network Based Cyber-Physical Systems
• Reachable Set Estimation and Verification for Neural Network Models of Nonlinear Dynamic Systems
• How to Learn a Model Checker