System for synthetical analyzing and monitoring safety of information on network

Abstract

The invention is in use for information safety domain of computer network. The invention includes control module for role access, protocol analysis and information capture module, blacklist / whitelist database, module for recognizing data types, text and image passive analysis modules, information data stream process node, process center, module for detecting hidden information of image, active analysis module for text image etc. Through protocol analysis and information capture module, the invention captures data transmitted under each protocol, and module for recognizing data types carries out recognition for captured information. The captured and recognized data are sent to subsequent module to carry out specific analysis. The process center sends out the process instructs to information data stream process node to execute intervening operation. The invention carries out analyzing and monitoring text and image information on network, and breaks and analyzes unhealthy information.

Description

technical field [0001] The invention relates to a system used in the field of computer network information security, specifically, a comprehensive analysis and monitoring system for online information security. Background technique [0002] Network content security monitoring and management is one of the key issues in the field of information security. It refers to protecting appropriate information and data from damage, and enabling appropriate people to properly transmit, obtain, and use appropriate information. Various networks such as INTERNET (Internet), local area network, backbone network, telecommunication network, mobile network, and next-generation network with softswitch as the core are all faced with the problem of network content security monitoring and management. However, the prior art is mainly based on blacklist and keyword matching, and the filtering algorithm is single, and the effect is not ideal. The blacklist-based strategy is a non-real-time filtering...

AI Technical Summary

Problems solved by technology

However, the existing technology is mainly based on blacklist and keyword matching, the filtering algorithm is single, and the effect is not ideal

The blacklist-based strategy is a non-real-time filtering method. The comprehensiveness of the blacklist has a great influence on the accuracy of content filtering, but too many blacklists will also affect the filtering speed. Such filtering strategies often change their domain names or network IP addresses. This is a situation that is difficult to handle with blacklist-based filtering strategies. Blacklist strategies rely more on prior experience, and the workload of information collection is heavy.

Keyword filtering is a kind of real-time filtering strategy commonly used in text filtering at present. The real-time filtering of keywords can solve the non-real-time weakness of the blacklist method to a certain extent, but there are also several shortcomings: keyword matching is a simple search Matching lacks semantic analysis, and misjudgments and missed judgments are more obvious. In addition, regarding the identification and filtering of pornographic information, if it is purely based on keyword matching, it is difficult to distinguish medical sexual information from pornographic information, and medical information will be misjudged. for pornography

However, the system uses manual grading to filter text and image content, and cannot automatically classify the above information, and cannot analyze and filter images with hidden information, and the operation of the system requires a large number of personnel to participate in monitoring, and the degree of automation is not high. High, low system processing efficiency and other disadvantages

Images