Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks

02/03/2017
by   Guy Katz, et al.
0

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.

READ FULL TEXT

Authors

page 1

page 2

page 3

page 4

11/05/2020

An SMT-Based Approach for Verifying Binarized Neural Networks

Deep learning has emerged as an effective approach for creating modern s...
12/21/2017

Reachable Set Computation and Safety Verification for Neural Networks with ReLU Activations

Neural networks have been widely used to solve complex real-world proble...
03/15/2019

Algorithms for Verifying Deep Neural Networks

Deep neural networks are widely used for nonlinear function approximatio...
10/07/2020

Global Optimization of Objective Functions Represented by ReLU Networks

Neural networks (NN) learn complex non-convex functions, making them des...
09/19/2017

Verifying Properties of Binarized Deep Neural Networks

Understanding properties of deep neural networks is an important challen...
05/03/2017

Formal Verification of Piece-Wise Linear Feed-Forward Neural Networks

We present an approach for the verification of feed-forward neural netwo...
03/09/2020

Finding Input Characterizations for Output Properties in ReLU Neural Networks

Deep Neural Networks (DNNs) have emerged as a powerful mechanism and are...

Code Repositories

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.