Research And Implementation Of Social Engineering Attack Detection System Based On Intelligent Agent

Social engineering is an attack that takes advantage of people's psychological weakness,establishes a trust relationship between the attacker and the victim by means of influence and persuasion,and finally achieves the purpose of accessing some sensitive data or privacy data.With the development of information technology,the Internet has become the most effective carrier of social engineering.The frequent attacks of social engineering,such as the US surveillance program PRISM,Hilary's mail scandal,data leakage of bank users pose a huge threat to the national and personal information property safety.At present,the existing social engineering attack detection technology is limited to a specific form of social engineering attack and there is a detection lag.Based on the above background,this paper uses honeypot technology,combined with the research of human attributes and social behavior in social engineering,constructs multiple intelligent agents,simulates user network behavior,and completes social engineering attack detection while attracting social engineering attack.The main work and innovation of this paper are as follows:(1)On the basis of a large number of social engineering cases,this paper summarizes the social engineering attack mode,puts forward the social engineering model,and puts forward the dialogic social engineering detection algorithm based on the intelligent agent.The intelligent agent interacts with the attacker by identifying the state in the attack mode,so as to maintain the trust relationship with the attacker,induce the attack and obtain more information at the same time,and detect social engineering attacks while protecting user privacy.(2)In the past,most of the features extracted from phishing email detection based on machine learning are text or link features.Considering the nature of social engineering attacks is to use deception and influence victims to make wrong decisions,this paper proposes a phishing email detection method based on persuasion principle,which is applied to intelligent agents.Experiments show that this method improves the accuracy of detection.(3)Design and implement a social engineering attack detection system based on intelligent agents.The system includes user management module,intelligent agent simulation module,social processing module,attack detection module,intelligent agent management module and log query module.The test results show that the system can effectively detect dialogic social engineering and phishing emails.