Litcius/Paper detail

Reachability analysis of deep ReLU neural networks using facet-vertex incidence

Xiaodong Yang, Taylor T. Johnson, Hoang-Dung Tran, Tomoya Yamaguchi, Bardh Hoxha, Danil Prokhorov

202120 citationsDOIOpen Access PDF

Abstract

Deep Neural Networks (DNNs) are powerful machine learning models for approximating complex functions. In this work, we provide an exact reachability analysis method for DNNs with Rectified Linear Unit (ReLU) activation functions. At its core, our set-based method utilizes a facet-vertex incidence matrix, which represents a complete encoding of the combinatorial structure of convex sets. When a safety violation is detected, our approach provides backtracking which determines the complete input set that caused the safety violation. The performance of our method is evaluated and compared to other state-of-the-art methods by using the ACAS Xu flight controller and other benchmarks.

Topics & Concepts

ReachabilityBacktrackingVertex (graph theory)Computer scienceArtificial neural networkSet (abstract data type)Facet (psychology)Incidence matrixAlgorithmTheoretical computer scienceArtificial intelligenceGraphSocial psychologyNode (physics)Big Five personality traitsStructural engineeringProgramming languageEngineeringPersonalityPsychologyAdversarial Robustness in Machine LearningSoftware Testing and Debugging TechniquesMachine Learning and Algorithms
Reachability analysis of deep ReLU neural networks using facet-vertex incidence | Litcius