LLM-based Property-based Test Generation for Guardrailing Cyber-Physical Systems

TL;DR

This paper introduces an automated method using Large Language Models to generate property-based tests for cyber-physical systems, enhancing safety verification at design and runtime.

Contribution

It presents a novel approach leveraging LLMs to extract properties and generate tests for CPSs, enabling automated safety guardrails both pre- and post-deployment.

Findings

Generated PBTs match manual properties well

High executability with minimal manual edits

Effective coverage of input space partitions

Abstract

Cyber-physical systems (CPSs) are complex systems that integrate physical, computational, and communication subsystems. The heterogeneous nature of these systems makes their safety assurance challenging. In this paper, we propose a novel automated approach for guardrailing cyber-physical systems using property-based tests (PBTs) generated by Large Language Models (LLMs). Our approach employs an LLM to extract properties from the code and documentation of CPSs. Next, we use the LLM to generate PBTs that verify the extracted properties on the CPS. The generated PBTs have two uses. First, they are used to test the CPS before it is deployed, i.e., at design time. Secondly, these PBTs can be used after deployment, i.e., at run time, to monitor the behavior of the system and guardrail it against unsafe states. We implement our approach in ChekProp and conduct preliminary experiments to evaluate the generated PBTs in terms of their relevance (how well they match manually crafted properties), executability (how many run with minimal manual modification), and effectiveness (coverage of the input space partitions). The results of our experiments and evaluation demonstrate a promising path forward for creating guardrails for CPSs using LLM-generated property-based tests.