Paper Info
Title
A Text Similarity-based Protocol Parsing Scheme for Industrial Internet of Things
Abstract
Protocol parsing is to discern and analyze packets' transmission fields, which plays an essential role in industrial security monitoring. The existing schemes parsing industrial protocols universally have problems, such as the limited parsing protocols, poor scalability, and high preliminary information requirements. This paper proposes a text similarity-based protocol parsing scheme (TPP) to identify and parse protocols for Industrial Internet of Things. TPP works in two stages, template generation and protocol parsing. In the template generation stage, TPP extracts protocol templates from protocol data packets by the cluster center extraction algorithm. The protocol templates will update continuously with the increase of the parsing packets' protocol types and quantities. In the protocol parsing phase, the protocol data packet will match the template according to the similarity measurement rules to identify and parse the fields of protocols. The similarity measurement method comprehensively measures the similarity between messages in terms of character position, sequence, and continuity to improve protocol parsing accuracy. We have implemented TPP in a smart industrial gateway and parsed more than 30 industrial protocols, including POWERLINK, DNP3, S7comm, Modbus-TCP, etc. We evaluate the performance of TPP by comparing it with the popular protocol analysis tool Netzob. The experimental results show that the accuracy of TPP is more than 20% higher than Netzob on average in industrial protocol identification and parsing.
Year
DOI
Venue
2021
10.1109/CSCWD49262.2021.9437659
PROCEEDINGS OF THE 2021 IEEE 24TH INTERNATIONAL CONFERENCE ON COMPUTER SUPPORTED COOPERATIVE WORK IN DESIGN (CSCWD)
Keywords
DocType
Citations 
protocol parsing, deep packet inspection, text similarity, industrial internet of things
Conference
0
PageRank 
References 
Authors
0.34
0
6
Name
Order
Citations
PageRank
Xiaoyu Jiang100.34
Tie Qiu289580.18
Xiaobo Zhou36416.25
Bin Zhang400.34
Ximin Sun500.68
Jiancheng Chi600.34