System and method for defending CC attack based on machine learning

Abstract

The invention discloses a system and a method for defending a CC attack based on machine learning. The system specifically comprises a training sample module, a machine learning algorithm module, a prediction sample module, a prediction judgment module and a CC attack protection system module. A log under the CC attack and a log not under the CC attackare analyzed and learned through the machine learning algorithm module, so that a trained prediction judgment module is obtained, and the module is used for carrying out real-time monitoring, analysis and capturing on log information on a server,and predicting whether to be under the CC attack. If an analysis result shows to be under the CC attack, the specific information is transmitted to the CC attack protection system, so that an IP address is shielded by the system. By means of the method for defending the CC attack, whether the server is under the CC attack can be rapidly and accurately predicted in real time, the capability of defending the CC attack of the server is greatly enhanced, and a protection function of network security is firmer.

Description

technical field [0001] The invention relates to the field of Internet information technology, in particular to a system and method for defending against CC attacks based on machine learning. Background technique [0002] With the continuous development of information technology and the continuous popularization of computers, the security problems of the Internet have become increasingly prominent. CC attack is one of the most common webpage attack methods, and its defense measures are essential in security protection. [0003] At present, when we judge whether the server is attacked by CC, we usually have the following limitations: 1) To judge whether the server is attacked by CC, we can only check manually, such as checking the system log, which will bring great harm to the staff. Workload; 2) After being attacked by CC for a period of time, the investigation will start, which leads to time-consuming and labor-intensive results; 3) It is impossible to monitor the system lo...

AI Technical Summary

Problems solved by technology

[0003] At present, when we judge whether the server is attacked by CC, we usually have the following limitations: 1) To judge whether the server is attacked by CC, we can only check manually, such as checking the system log, which will bring great harm to the staff. Workload; 2) After being attacked by CC for a period of time, the investigation will start, which leads to time-consuming and labor-intensive results; 3) It is impossible to monitor the system log in real time manually, and it is impossible to detect CC attacks in time, which may cause the server to fail to connect normally

Images