Reverse Engineering of Industrial Control Protocol By XGBoost with V-gram
Rui Wang, Yijie Shi, Jinkou Ding · 2020
Protocol reverse engineering is essential to information security of industrial control systems. In this paper, we propose a V-gram method, which takes variable gram as input of XGBoost. In view of the periodic and structurally fixed characteristics of industrial control protocol, progressive multi-sequence alignment algorithm is used to cluster initial message samples for traffic with the same payload length. V-gram is generated after the variable domain and fixed domain of message sequences are separated, and feature words are extracted by XGBoost model. The states of data packets are classified and tagged with XGBoost, so as to realize the construction of FSM model. Experimental results show that the proposed approach is effective in mining junior semantic information for industrial control protocols.