T
Taylor T. Johnson
Researcher at Vanderbilt University
Publications - 56
Citations - 1815
Taylor T. Johnson is an academic researcher from Vanderbilt University. The author has contributed to research in topics: Artificial neural network & Reachability. The author has an hindex of 17, co-authored 56 publications receiving 990 citations. Previous affiliations of Taylor T. Johnson include University of Nebraska–Lincoln & University of Texas at Arlington.
Papers
More filters
Journal ArticleDOI
Output Reachable Set Estimation and Verification for Multilayer Neural Networks
TL;DR: In this article, the output reachable estimation and safety verification problems for multilayer perceptron (MLP) neural networks are addressed, and an automated safety verification is developed based on the output reachedable set estimation result.
Journal ArticleDOI
Detection of False-Data Injection Attacks in Cyber-Physical DC Microgrids
TL;DR: This paper presents a framework to detect possible false-data injection attacks (FDIAs) in cyber-physical dc microgrids, and a prototype tool is extended to instrument SLSF models, obtain candidate invariants, and identify FDIA.
Book ChapterDOI
NNV: The Neural Network Verification Tool for Deep Neural Networks and Learning-Enabled Cyber-Physical Systems
Hoang-Dung Tran,Xiaodong Yang,Diego Manzanas Lopez,Patrick Musau,Luan Viet Nguyen,Weiming Xiang,Stanley Bak,Taylor T. Johnson +7 more
TL;DR: The Neural Network Verification software tool is presented, a set-based verification framework for deep neural networks (DNNs) and learning-enabled cyber-physical systems (CPS) that provides exact and over-approximate reachability analysis schemes for linear plant models and FFNN controllers with piecewise-linear activation functions.
Book ChapterDOI
Star-based reachability analysis of deep neural networks
Hoang-Dung Tran,Diago Manzanas Lopez,Patrick Musau,Xiaodong Yang,Luan Viet Nguyen,Weiming Xiang,Taylor T. Johnson +6 more
TL;DR: This paper proposes novel reachability algorithms for both exact (sound and complete) and over-approximation (sound) analysis of deep neural networks (DNNs) that uses star sets as a symbolic representation of sets of states to provide an effective representation of high-dimensional polytopes.
Journal ArticleDOI
Signal Temporal Logic-Based Attack Detection in DC Microgrids
TL;DR: Signal temporal logic (STL) detection of two major types of cyber attacks, namely false-data injection attacks and denial-of-service attacks, are presented.