Penetration behavior prediction algorithm based on machine learning

• Main Authors: DONG LIMIAN, WANG YING, GUO YULING, XI BO, LIU SHUO, LIU WEINA, CHEN ZE, ZHANG JUNYAN, CHANG JIE, LIU XIN, WANG CHUNPU, ZUO XIAOJUN, DONG NA, HOU BOTAO, LIU HUIYING, ZHAO JIANBIN, KANG ZHIZENG
• Format: Patent
• Language: Chinese; English
• Published: 06.03.2020
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; PHYSICS

The invention relates to the technical field of information security, in particular to a penetration behavior prediction algorithm based on machine learning, which aims at all behavior information andenvironmental data in the current network environment, predicts the next effective penetration behavior according to the existing penetration experience of penetration experts, and plays a role in assisting a user in carrying out a penetration test. The method comprises the following steps: data collection: collecting permeation behavior data and site feature data of a permeation expert for a target site; wherein the permeation behavior data comprises actions of experts, tools used by the experts, commands input by the experts and observation objects of the experts; wherein the site feature data comprises domain names, services, ports and contents of sites; and data conversion: cutting the collected permeation behavior data into inseparable parts, and replacing all the inseparable parts with numbers in sequence,