NExG: Provable and Guided State Space Exploration of Neural Network Control Systems using Sensitivity Approximation
This addresses the challenge of verifying and testing neural network control systems, which is critical for safety-critical applications, though it appears incremental by building on existing falsification methods.
The paper tackles the problem of state space exploration for neural network control systems by proposing a guided method using sensitivity approximation, achieving significant improvements in explainability and convergence rate compared to earlier techniques.
We propose a new technique for performing state space exploration of closed loop control systems with neural network feedback controllers. Our approach involves approximating the sensitivity of the trajectories of the closed loop dynamics. Using such an approximator and the system simulator, we present a guided state space exploration method that can generate trajectories visiting the neighborhood of a target state at a specified time. We present a theoretical framework which establishes that our method will produce a sequence of trajectories that will reach a suitable neighborhood of the target state. We provide thorough evaluation of our approach on various systems with neural network feedback controllers of different configurations. We outperform earlier state space exploration techniques and achieve significant improvement in both the quality (explainability) and performance (convergence rate). Finally, we adopt our algorithm for the falsification of a class of temporal logic specification, assess its performance against a state-of-the-art falsification tool, and show its potential in supplementing existing falsification algorithms.