Detecting contradictions from IoT protocol specification documents based on neural generated knowledge graph

Xinguo Feng; Yanjun Zhang; Mark Huasong Meng; Yansong Li; Chegne Eu Joe; Zhe Wang; Guangdong Bai

doi:10.1016/j.isatra.2023.04.025

Detecting contradictions from IoT protocol specification documents based on neural generated knowledge graph

ISA Trans. 2023 Oct:141:10-19. doi: 10.1016/j.isatra.2023.04.025. Epub 2023 Apr 29.

Authors

Xinguo Feng¹, Yanjun Zhang², Mark Huasong Meng³, Yansong Li⁴, Chegne Eu Joe⁴, Zhe Wang⁵, Guangdong Bai⁴

Affiliations

¹ The University of Queensland, Australia. Electronic address: s.feng@uq.edu.au.
² Cyber Security Research and Innovation (CSRI), Deakin University, Australia.
³ Institute for Infocomm Research, A*STAR, Singapore; National University of Singapore, Singapore.
⁴ The University of Queensland, Australia.
⁵ Griffith University, Australia.

PMID: 37164876
DOI: 10.1016/j.isatra.2023.04.025

Abstract

Due to the boom of Internet of Things (IoT) in recent years, various IoT devices are connected to the Internet and communicate with each other through network protocols such as the Constrained Application Protocol (CoAP). These protocols are typically defined and described in specification documents, such as Request for Comments (RFC), which are written in natural or semi-formal languages. Since developers largely follow the specification documents when implementing web protocols, they have become the de facto protocol specifications. Therefore, it must be ensured that the descriptions in them are consistent to avoid technological issues, incompatibility, security risks, or even legal concerns. In this work, we propose Neural RFC Knowledge Graph (NRFCKG), a neural network-generated knowledge graph based contradictions detection tool for IoT protocol specification documents. Our approach can automatically parse the specification documents and construct knowledge graphs from them through entity extraction, relation extraction, and rule extraction with large language models. It then conducts an intra-entity and inter-entity contradiction detection over the generated knowledge graph. We implement NRFCKG and apply it to the most extensively used messaging protocols in IoT, including the main RFC (RFC7252) of CoAP, the specification document of MQTT, and the specification document of AMQP. Our evaluation shows that NRFCKG generalizes well to other specification documents and it manages to detect contradictions from these IoT protocol specification documents.

Keywords: Contradiction detection; Internet of things; Large language models; Natural language processing; Web protocol.