Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks
This addresses the critical need for formal verification in safety-critical applications like unmanned aircraft systems, representing a significant advance over prior methods.
The authors tackled the problem of providing formal guarantees for deep neural networks in safety-critical systems by developing Reluplex, a scalable SMT solver based on the simplex method extended for ReLU activations. They demonstrated its effectiveness by verifying properties of ACAS Xu networks an order of magnitude larger than previously possible.
Deep neural networks have emerged as a widely used and effective means for tackling complex, real-world problems. However, a major obstacle in applying them to safety-critical systems is the great difficulty in providing formal guarantees about their behavior. We present a novel, scalable, and efficient technique for verifying properties of deep neural networks (or providing counter-examples). The technique is based on the simplex method, extended to handle the non-convex Rectified Linear Unit (ReLU) activation function, which is a crucial ingredient in many modern neural networks. The verification procedure tackles neural networks as a whole, without making any simplifying assumptions. We evaluated our technique on a prototype deep neural network implementation of the next-generation airborne collision avoidance system for unmanned aircraft (ACAS Xu). Results show that our technique can successfully prove properties of networks that are an order of magnitude larger than the largest networks verified using existing methods.