The Marabou Framework for Verification and Analysis of Deep Neural Networks

Katz, Guy; Huang, Derek A.; Ibeling, Duligur; Julian, Kyle D.; Lazarus, Christopher; Lim, Rachel; Shah, Parth; Thakoor, Shantanu; Wu, Haoze; Zeljić, Aleksandar; Dill, David L.; Kochenderfer, Mykel J.; Barrett, Clark

doi:10.1007/978-3-030-25540-4_26

book chapterLecture notes in computer scienceJan 1, 2019HYBRID OA

The Marabou Framework for Verification and Analysis of Deep Neural Networks

GKGuy Katz DADerek A. Huang DIDuligur Ibeling KDKyle D. Julian CLChristopher Lazarus

Hebrew University of Jerusalem · Stanford University

Indexed incrossref

Abstract

Deep neural networks are revolutionizing the way complex systems are designed. Consequently, there is a pressing need for tools and techniques for network analysis and certification. To help in addressing that need, we present Marabou, a framework for verifying deep neural networks. Marabou is an SMT-based tool that can answer queries about a network’s properties by transforming these queries into constraint satisfaction problems. It can accommodate networks with different activation functions and topologies, and it performs high-level reasoning on the network that can curtail the search space and improve performance. It also supports parallel execution to further enhance scalability. Marabou accepts multiple…

Citation impact

476

total citations

FWCI: 59.50
Percentile: 100%
References: 22

Citations per year

Authors

13

Topics & keywords

Topics

Keywords

Computer science
Scalability
Artificial neural network
Network topology
Artificial intelligence
Protocol (science)
Distributed computing
Constraint satisfaction problem

No related works found for this paper.