The Key Technologies to Realize the Profiling and Positioning of Key Personnel Based on Public Information Such as Social Accounts and IP

• Published in: 2022 IEEE 2nd International Conference on Mobile Networks and Wireless Communications (ICMNWC) pp. 1 - 4
• Main Authors: Cheng, Kai, Wang, Qiang, Wu, Zhan, Tan, Lintao, Xiao, Dongling, Zou, Chengcheng
• Format: Conference Proceeding
• Language: English
• Published: IEEE 02.12.2022
• Subjects: attacker portrait; Face recognition; key personnel; Network intrusion detection; Network security; Prediction algorithms; public information; Real-time systems; Resists; security threat; Wireless communication
• DOI: 10.1109/ICMNWC56175.2022.10031850

In recent years, with the rapid development and application of emerging technologies such as the Internet, cloud computing, and big data, there has been a substantial increase in threats to intrusions into networks and information systems. Plays an important role in preventing security threats and protecting the network from attacks. Over the years, attackers and defenders have been at war with each other, with new, combined or higher-level attack patterns emerging. Based on public information such as social accounts and IP, this paper describes network intrusion attacks from multiple dimensions such as attackers, attack targets, and attack methods. The key technology for the complete construction and positioning of the portrait. At the same time, this paper combines the advantages of deep learning and generative methods to build a deep generative model to detect and identify attacks. The construction of attacker portraits has become a network intrusion detection and defense process, analyzing the attacker's intention, and effectively restoring and predicting the attack process. It is a good solution to the problems that traditional machine learning methods suffer from low detection rate and high false alarm rate. The final results of the research show that the processing time can be greatly reduced after the algorithm is optimized. The processing time of IP addresses is determined by The increase from 266s to 636s is because each word segment needs to be compared with all addresses in the address library, and the processing time of all programs increases rapidly with the number of statements.