Algorithms for Verifying Deep Neural Networks

📖 Description

Algorithms for Verifying Deep Neural Networks Changliu Liu Carnegie Mellon University [email removed]Tomer Arnon Stanford University [email removed]Christopher Lazarus Stanford University [email removed] Christopher Strong Stanford University [email removed]Clark Barrett Stanford University [email removed]Mykel J. Kochenderfer Stanford University [email removed] October 11, 2020 Abstract Deep neural networks are widely used for nonlinear function approximation, with applications ranging from computer vision to control. Although these networks involve the composition of simple arithmetic operations, it can be very challenging to verify whether a particular network satisfies certain input-output properties. This article surveys methods that have emerged recently for soundly verifying such properties. These methods borrow insights from reachability analysis, optimization, and search. We discuss fundamental differences and connections between existing alg...

📊 Game Impacts

💭 Reactions

🔗 Sources

• [1] https://arxiv.org/abs/1903.06758