Information leakage detecting method and device

Abstract

The invention discloses an information leakage detecting method and device, which comprises the following steps of receiving a request message sent by a channel party; matching a parameter included in the request message and a key word obtained from prior machine learning, and obtaining a matching degree between the parameter and the key word based on a matching result; and when the matching degree is greater than a preset threshold, determining that information of the request message is disclosed, and recording the relative information of the request message. The invention also discloses an information leakage detecting device. According to the information leakage detecting method and the device, more key words can be identified automatically through the machine learning; sensitive information can be identified substantially and effectively; duplicate work of safety testers can be reduced; and efficiency of detecting the information leakage can be improved and risks of leaking information can be reduced.

Description

technical field [0001] The present invention relates to the technical field of information security, in particular to an information leakage detection method and device. Background technique [0002] At present, in order to protect the user's information security, the server only pre-defines specific keywords corresponding to sensitive information during the process of detecting information leakage through the web application vulnerability scanner, such as email, username, etc., and compares the parameters of the scanning record with the key If there is a parameter consistent with the keyword in the scanned record parameters, it means that there is a clear text transmission of sensitive information, that is, there is a risk of information leakage. However, if USERNAME appears in the parameter in the http request of the newly developed system, and the specific keyword includes username but does not include USERNAME, the match cannot be identified, or if uname appears in the p...

AI Technical Summary

Problems solved by technology

However, if USERNAME appears in the parameter in the http request of the newly developed system, and the specific keyword includes username but does not include USERNAME, the match cannot be identified, or if uname appears in the parameter in the http request, the match cannot be identified, which may lead to sensitive information plaintext Transmission, Risk of Information Disclosure

Images