Seminar: Verifying Neural Networks in Autonomous Cyber-Physical Systems

Sunday, June 2, 2019

Taylor T. Johnson, Assistant Professor, Vanderbilt University

Location and time:
Monday, June 3 at 1pm in E7-4053

The ongoing renaissance in artificial intelligence (AI) has led to the advent of machine learning methods deployed within components for sensing, actuation, and control in safety-critical cyber-physical systems (CPS), and is enabling autonomy in such systems, such as autonomous vehicles, swarm robots, and other CPS with learning-enabled components (LECs). However, as demonstrated in part through recent accidents in semi-autonomous/autonomous CPS and by adversarial machine learning attacks, ensuring such components operate reliably in all scenarios is extraordinarily challenging. We will discuss methods for assuring safety and security specifications in autonomous CPS using our nnv (neural network verification) tool (, which has been applied to verify specifications in closed-loop autonomous CPS for adaptive cruise control (ACC) and autonomous emergency braking (AEB) systems in motor vehicles. We will conclude with some architectural solutions that enhance trust and safety assurance in autonomous CPS, building on supervisory control with the Simplex architecture using real-time reachability, and will discuss future research directions for enhancing trust of machine learning components within CPS that we are exploring within DARPA Assured Autonomy and NSA/DoD Science of Security Lablet projects.

Dr. Taylor T. Johnson is an Assistant Professor of Computer Engineering (CmpE), Computer Science (CS), and Electrical Engineering (EE) in the Department of Electrical Engineering and Computer Science (EECS) in the School of Engineering (VUSE) at Vanderbilt University (since August 2016), where he directs the Verification and Validation for Intelligent and Trustworthy Autonomy Laboratory (VeriVITAL) and is a Senior Research Scientist in the Institute for Software Integrated Systems (ISIS). Dr. Johnson serves as the President of a medical information technology startup firm, CelerFama, Inc., and as the Chief Technology Officer (CTO) of Verivital, LLC, both of which serve for technology transfer and commercialization of his research group's results to industry. Dr. Johnson was previously an Assistant Professor of Computer Science and Engineering (CSE) at the University of Texas at Arlington (September 2013 to August 2016). Dr. Johnson earned a PhD in Electrical and Computer Engineering (ECE) from the University of Illinois at Urbana-Champaign in 2013, where he worked in the Coordinated Science Laboratory with Prof. Sayan Mitra, and earlier earned an MSc in ECE at Illinois in 2010 and a BSEE from Rice University in 2008. Dr. Johnson has published over 70 papers on formal methods and their applications across cyber-physical systems (CPS) domains, such as power and energy, aerospace, automotive, transportation, biotechnology, and robotics, one of which was awarded an ACM Best Software Repeatability Award. Dr. Johnson is a 2018 and 2016 recipient of the AFOSR Young Investigator Program (YIP) award, a 2015 recipient of the National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) Research Initiation Initiative (CRII), and his research is / has been supported by AFOSR, ARO, AFRL, DARPA, NSA, NSF, the MathWorks, NVIDIA, ONR, Toyota, and USDOT. Dr. Johnson is a member of AAAI, AAAS, ACM, AIAA, IEEE, and SAE, and is a TN Professional Engineer Intern (EiT) with Professional Engineer (PE) licensure pending.

  1. 2019 (6)
    1. December (2)
    2. November (1)
    3. August (1)
    4. June (1)
    5. January (1)
  2. 2018 (7)
    1. October (3)
    2. March (2)
    3. January (2)
  3. 2017 (8)
  4. 2016 (6)
  5. 2015 (8)
  6. 2014 (1)
  7. 2012 (1)
  8. 2011 (4)