Alert button
Picture for David Dill

David Dill

Alert button

Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks

May 19, 2017
Guy Katz, Clark Barrett, David Dill, Kyle Julian, Mykel Kochenderfer

Figure 1 for Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks
Figure 2 for Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks
Figure 3 for Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks
Figure 4 for Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks

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.

* This is the extended version of a paper with the same title that appeared at CAV 2017 
Viaarxiv icon