A Modular Approach to Verification of Learning Components in Cyber-Physical Systems

January 19, 2023 • Conference Paper

By

Lijing Zhai (Georgia Institute of Technology), Aris Kanellopoulos (Georgia Institute of Technology), Filippos Fotiadis (Georgia Institute of Technology), Kyriakos G. Vamvoudakis (Georgia Institute of Technology), and Jerome Hugues

In this paper, the authors provide a framework that enables the operator of a cyber-physical system to assess its operation in the presence of data-driven, learning components.

Publisher

American Institute of Aeronautics and Astronautics

DOI (Digital Object Identifier)

10.2514/6.2023-0131

Topic or Tag

Abstract

In this work, we aim to provide a framework that enables the operator of a cyber-physical system to assess its operation in the presence of data-driven, learning components. Towards this, we leverage Architecture Analysis & Design Language (AADL) to provide a representation of the system’s components and their interconnections to construct a modular environment allowing for the inclusion of different detection and learning mechanisms, which supports a full model-based development including system specification, analysis, system tuning, integration, and upgrade over the lifecycle. Specifically, we illustrate the propagation of errors throughout system components due to adversarial attacks in the learning processes for a UAV system and obtain safety tolerance thresholds.

Software Engineering Institute