Privacy leakage risk detection method, device and system

Through periodic feature comparison and scanning detection, the feature comparison type, backup frequency and scanning granularity are adjusted based on the average error rate and abnormal login times, and the problem of low accuracy of privacy leakage detection in the existing technology is solved, and the identification of privacy data is improved and Detection accuracy.

CN118194336BActive Publication Date: 2024-11-26BEIJING WANCHENG RUIXUN TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410026442.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-01-09
Publication Date
2024-11-26
Estimated Expiration
2044-01-09

AI Technical Summary

Technical Problem

The existing privacy leakage risk detection methods have reduced detection accuracy due to inaccurate determination of stability reflected by the average error rate.

Method used

Through periodic feature comparison and scanning detection, the feature comparison type, backup frequency and scanning granularity are determined based on the average error rate and the number of abnormal logins, so as to improve data identification accuracy and detection accuracy.

Benefits of technology

It enhances the possibility of identification and detection accuracy of privacy data, reduces the risk of privacy leakage, and improves the accuracy and effectiveness of detection.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118194336B_ABST
    Figure CN118194336B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of data processing technology, and in particular to a method, device and system for detecting privacy leakage risks, the method comprising: performing periodic feature comparison between a number of data on a browsing page and feature points of privacy data stored in a database to identify the privacy data, and performing scanning and detection on a number of running processes of the browsing page to determine the location of the privacy leakage risk and leakage risk information; determining the number of feature comparison types in the database based on the average error rate of a number of scanning and detection processes; determining the backup frequency of privacy data based on the number of abnormal logins per unit detection cycle, or determining the scanning granularity of the browsing page information based on the number of abnormal logins per unit detection cycle and the number of privacy leakage methods. The present invention achieves a reduction in the risk of privacy leakage and an improvement in detection accuracy.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method, device and system for detecting privacy leakage risks. Background Art

[0002] With the popularization of the Internet and the development of big data technology, data has become an important asset for enterprises and individuals. However, data is prone to privacy leakage during storage, transmission and processing, resulting in the leakage of personal privacy and sensitive information. In order to protect data security and privacy, it is necessary to study an effective privacy leakage risk detection method.

[0003] Chinese Patent Publication No.: CN111753328B discloses a method and system for detecting the risk of privacy data leakage, the method comprising: processing the behavior data of a target user in a current time period through a streaming processing node to obtain the current feature information of the target user in each target dimension; obtaining the current feature information and the historical feature information of the target user in each target dimension through an analysis node, and detecting whether the target user has a risk of privacy data leakage based on the current feature information and the historical feature information; wherein the above-mentioned historical feature information is obtained by processing the historical behavior data of the target user in a historical time period by a batch processing node; the time length of the historical time period is greater than the time length of the current time period; it can be seen that the method and system for detecting the risk of privacy data leakage have the following problems: the detection accuracy is reduced due to the inaccurate judgment of the stability of privacy leakage detection reflected by the average error rate of several scanning detection processes. Summary of the invention

[0004] To this end, the present invention provides a privacy leakage risk detection method, device and system to overcome the problem in the prior art that the stability of privacy leakage detection reflected by the average error rate of several scanning detection processes is inaccurate, resulting in reduced detection accuracy.

[0005] To achieve the above-mentioned purpose, the present invention provides a method for detecting privacy leakage risks, comprising the following steps: performing periodic feature comparison on a number of data on a browsing page and feature points of privacy data stored in a database to identify the privacy data, and scanning and detecting a number of running processes of the browsing page to determine the privacy leakage risk information; determining the number of feature comparison types in the database based on the average error rate of several scanning and detection processes, or, performing a preliminary judgment on the effectiveness of the scanning and detection process based on the average error rate of the several scanning and detection processes and the number of abnormal logins in a unit detection cycle, and counting the number of abnormal logins in the unit detection cycle; if the effectiveness of the scanning and detection process is determined to be unsatisfactory based on the number of abnormal logins in the unit detection cycle, then determining the backup frequency of the privacy data, or, determining the scanning granularity of the browsing page information based on the number of abnormal logins in the unit detection cycle and the number of privacy leakage modes; obtaining the time required for completing the privacy leakage alarm after the number of feature comparison types in the database is determined, and re-determining the number of feature comparison types in the database based on the time required for the privacy leakage alarm.

[0006] Furthermore, the step of determining the number of feature comparison types in the database includes:

[0007] Obtaining the error rate of several detection cycles and calculating the average error rate of several scanning detection processes;

[0008] Comparing the average error rate of the plurality of scanning detection processes with a preset first error rate and a preset second error rate respectively;

[0009] If the average error rate of the several scanning detection processes is greater than the preset first error rate and less than or equal to the preset second error rate, it is determined that the stability of privacy leakage detection is lower than the allowable range, and the number of feature comparison types in the database is determined.

[0010] Furthermore, the number of feature comparison types in the database is determined by the difference between an average error rate of the plurality of scanning detection processes and the preset first error rate.

[0011] Furthermore, the step of determining the backup frequency of the private data includes:

[0012] If the average error rate of the plurality of scanning and detection processes is greater than the preset second error rate, it is preliminarily determined that the effectiveness of the scanning and detection process is lower than the allowable range, and the number of abnormal logins in the unit detection cycle is obtained;

[0013] The number of abnormal logins in the unit detection period is compared with a preset first number and a preset second number respectively;

[0014] If the number of abnormal logins in the unit detection cycle is greater than the preset second number, it is secondarily determined that the effectiveness of the privacy leakage risk scan is lower than the allowable range, and the backup frequency of the privacy data is determined.

[0015] Furthermore, the backup frequency of the privacy data is determined based on the difference between the number of abnormal logins in the unit detection period and the preset second number.

[0016] Furthermore, the step of determining the scanning granularity of the information of the browsed page includes:

[0017] If the number of abnormal logins in the unit detection period is greater than the preset first number and less than or equal to the preset second number, the number of privacy leakage methods is obtained;

[0018] Comparing the number of privacy leakage methods with a preset number;

[0019] If the number of the privacy leakage modes is greater than the preset number, it is determined that the comprehensiveness of the risk scan is lower than the allowable range, and the scanning granularity of the information on the browsed page is determined.

[0020] Furthermore, the scanning granularity of the determined browsing page information is inversely proportional to the difference between the number of the privacy leakage modes and the preset number.

[0021] Further, the step of re-determining the number of feature comparison types in the database includes:

[0022] Comparing the time required for the privacy leakage alarm with a preset time;

[0023] If the time required for the privacy leakage alarm is longer than the preset time, it is determined that the real-time performance of risk detection is lower than the allowable range, and the number of feature comparison types in the database is redetermined based on the difference between the time required for the privacy leakage alarm and the preset time.

[0024] The present invention also provides a privacy leakage risk detection device, comprising:

[0025] A data analysis module, used to periodically compare a certain amount of data on the browsing page with the privacy data feature points stored in the database to identify the privacy data, and to scan and detect a certain number of running processes of the browsing page to determine the privacy leakage risk information;

[0026] A comparison control module, connected to the data analysis unit, for determining the number of feature comparison types in the database according to an average error rate of several scanning detection processes, and re-determining the number of feature comparison types in the database according to the required time for a privacy leakage alarm under a first condition, wherein the first condition is when the number of feature comparison types in the database is determined;

[0027] A scanning validity monitoring module, which is respectively connected to the data analysis module and the comparison control module, is used to determine the backup frequency of privacy data based on the average error rate of the several scanning detection processes and the number of abnormal logins in a unit detection cycle, or to determine the scanning granularity of the information on the browsing page based on the number of abnormal logins in the unit detection cycle and the number of privacy leakage methods.

[0028] The present invention also provides a privacy leakage risk detection system, comprising a privacy leakage risk detection device and a control panel for displaying a privacy leakage alarm and privacy leakage risk information.

[0029] A data analysis module, used to periodically compare a certain amount of data on the browsing page with the privacy data feature points stored in the database to identify the privacy data, and to scan and detect a certain number of running processes of the browsing page to determine the privacy leakage risk information;

[0030] A comparison control module, connected to the data analysis unit, for determining the number of feature comparison types in the database according to an average error rate of several scanning detection processes, and re-determining the number of feature comparison types in the database according to the required time for a privacy leakage alarm under a first condition, wherein the first condition is when the number of feature comparison types in the database is determined;

[0031] A scanning validity monitoring module, which is respectively connected to the data analysis module and the comparison control module, is used to determine the backup frequency of privacy data based on the average error rate of the several scanning detection processes and the number of abnormal logins in a unit detection cycle, or to determine the scanning granularity of the information on the browsing page based on the number of abnormal logins in the unit detection cycle and the number of privacy leakage methods.

[0032] Compared with the prior art, the beneficial effect of the present invention lies in that, when the method of the present invention detects the risk of privacy leakage, due to defects in data identification, the privacy data cannot be correctly identified, thereby causing the leakage of privacy data. By increasing the number of feature comparison types in the database, the possibility of privacy data being identified is increased and the accuracy of data identification is improved, thereby further achieving the reduction of privacy leakage risks and the improvement of detection accuracy.

[0033] Furthermore, when the method of the present invention detects the risk of privacy leakage, the scanning degree decreases due to the increase in the amount of data acquired, which in turn increases the degree of privacy data leakage. By reducing the backup frequency of privacy data, reducing the amount of privacy data updated in real time, and reducing the amount of privacy data acquired by viruses or other privacy data leakage methods, the risk of privacy leakage is further reduced and the detection accuracy is improved.

[0034] Furthermore, when the method of the present invention detects the risk of privacy leakage, since the change in the privacy data leakage mode leads to the inability to perform normal identification and thus causes the degree of privacy data leakage to increase, the scanning granularity of the information on the browsed page is reduced according to the number of privacy leakage modes, so that the scanning tool can analyze the privacy data more carefully and more easily discover potential vulnerabilities therein, thereby improving the accuracy of vulnerability detection, further achieving the reduction of privacy leakage risks and the improvement of detection accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 This is an overall flow chart of a method for detecting privacy leakage risk according to an embodiment of the present invention;

[0036] Figure 2 A specific flow chart of determining the number of feature comparison types in a database for a method for detecting privacy leakage risk according to an embodiment of the present invention;

[0037] Figure 3 A logic block diagram of determining the backup frequency of private data in a method for detecting a privacy leakage risk according to an embodiment of the present invention;

[0038] Figure 4 This is a block diagram of the overall structure of a privacy leakage risk detection system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0039] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0040] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0041] See also Figure 1 , Figure 2 , Figure 3 as well as Figure 4As shown, they are respectively an overall flow chart of a method for detecting privacy leakage risk according to an embodiment of the present invention, a specific flow chart for determining the number of feature comparison types in a database, a logic block diagram for determining the backup frequency of privacy data, and an overall structural block diagram of a system for detecting privacy leakage risk. A method for detecting privacy leakage risk according to the present invention comprises the following steps:

[0042] Periodically comparing a certain amount of data on the browsing page with the privacy data feature points stored in the database to identify the privacy data, and scanning and detecting a certain number of running processes on the browsing page to determine privacy leakage risk information;

[0043] Determine the number of feature comparison types in the database based on the average error rate of several scanning and detection processes, or make a preliminary judgment on the effectiveness of the scanning and detection process based on the average error rate of several scanning and detection processes and the number of abnormal logins per unit detection cycle and count the number of abnormal logins per unit detection cycle;

[0044] If the effectiveness of the scanning detection process is determined to be unsatisfactory based on the number of abnormal logins in the unit detection period, the backup frequency of the privacy data is determined, or the scanning granularity of the information on the browsed page is determined based on the number of abnormal logins in the unit detection period and the number of privacy leakage methods;

[0045] The time required for the privacy leakage alarm after the number of feature comparison types in the database is determined is obtained, and the number of feature comparison types in the database is re-determined based on the time required for the privacy leakage alarm.

[0046] Specifically, privacy leakage risk information includes the leakage location, the amount of leaked data, and the time node of the leakage.

[0047] Specifically, the identification process is to compare a certain amount of data with the privacy data feature points stored in the database. If the certain amount of data meets the privacy data feature points, such as character sequence features, geographic location features or age features, then the data is determined to be privacy data.

[0048] Specifically, when an abnormal login occurs on a browsing page, such as logging in from a different location, a privacy breach alert is issued.

[0049] Specifically, the calculation formula for the average error rate of several scanning detection processes is:

[0050]

[0051] Among them, P is the average error rate of several scanning and detection processes, pj is the number of information leakage in the jth detection cycle, n is the number of detection cycles, n is a natural number greater than or equal to 1, and p is the number of scanning and detection in one cycle.

[0052] Specifically, abnormal logins include logging in from a different location, logging in from different devices, and logging in at abnormal times.

[0053] Specifically, the data in the database includes user geographic location data, image data, and order data.

[0054] Specifically, the scanning granularity of the browsing page information is the degree of detail of scanning several running processes of the browsing page. The scanning granularity of the browsing page information can be the number of characters, the amount of data, and the image area.

[0055] Please continue reading Figure 2 As shown, the step of determining the number of feature comparison types in the database includes:

[0056] Obtaining the error rate of several detection cycles and calculating the average error rate of several scanning detection processes;

[0057] Comparing the average error rate of the plurality of scanning detection processes with a preset first error rate and a preset second error rate respectively;

[0058] If the average error rate of the several scanning detection processes is greater than the preset first error rate and less than or equal to the preset second error rate, it is determined that the stability of privacy leakage detection is lower than the allowable range, and the number of feature comparison types in the database is determined.

[0059] Please continue reading Figure 2 As shown, the number of feature comparison types in the database is determined by the difference between the average error rate of the several scanning detection processes and the preset first error rate.

[0060] Specifically, the average error rate of several scanning detection processes is recorded as P, the preset first error rate is recorded as P1, the preset second error rate is recorded as P2, the difference between the average error rate of several scanning detection processes and the preset first error rate is recorded as △P, and the preset error rate difference is recorded as △P0;

[0061] Determine the number of feature comparison types in the database by the difference between the average error rate of the plurality of scanning detection processes and the preset first error rate, that is, adjust the number of feature comparison types in the database according to the error rate difference;

[0062] If △P≤△P0, adjust the number V of feature comparison types in the database to V'=Ceil(7V / 5);

[0063] If ΔP>ΔP0, the number V of feature comparison types in the database is adjusted to V'=Ceil(7V / 3).

[0064] When the method of the present invention detects the risk of privacy leakage, due to defects in data identification, the privacy data cannot be correctly identified, which leads to the leakage of privacy data. By increasing the number of feature comparison types in the database, the possibility of privacy data being identified is increased and the accuracy of data identification is improved, thereby further reducing the risk of privacy leakage and improving the detection accuracy.

[0065] Please continue reading Figure 1 As shown, the step of determining the backup frequency of the private data includes:

[0066] If the average error rate of the plurality of scanning and detection processes is greater than the preset second error rate, it is preliminarily determined that the effectiveness of the scanning and detection process is lower than the allowable range, and the number of abnormal logins in the unit detection cycle is obtained;

[0067] The number of abnormal logins in the unit detection period is compared with a preset first number and a preset second number respectively;

[0068] If the number of abnormal logins in the unit detection cycle is greater than the preset second number, it is secondarily determined that the effectiveness of the privacy leakage risk scan is lower than the allowable range, and the backup frequency of the privacy data is determined.

[0069] The backup frequency of the privacy data is determined based on the difference between the number of abnormal logins in the unit detection period and the preset second number.

[0070] Specifically, the number of abnormal logins in a unit detection cycle is recorded as C, the preset first number is recorded as C1, the preset second number is recorded as C2, the difference between the number of abnormal logins in a unit detection cycle and the preset second number is recorded as △C, △C=C-C2 is set, and the preset number difference is recorded as △C0.

[0071] The method for determining the backup frequency of the privacy data based on the difference between the number of abnormal logins in the unit detection cycle and the preset second number is:

[0072] If △C≤△C0, the backup frequency H of the privacy data is adjusted using the preset second frequency adjustment coefficient α2;

[0073] If △C>△C0, the backup frequency H of the privacy data is adjusted using the preset first frequency adjustment coefficient α1;

[0074] Among them, 0<α1<α2<1, the backup frequency of the adjusted privacy data is H'=H×αi, αi is the preset i-th frequency adjustment coefficient, and i=1,2 is set.

[0075] When the method of the present invention detects the risk of privacy leakage, the scanning degree decreases due to the increase in the amount of data acquired, which in turn increases the degree of privacy data leakage. By reducing the backup frequency of privacy data, reducing the amount of privacy data updated in real time, and reducing the amount of privacy data acquired by viruses or other privacy data leakage methods, the risk of privacy leakage is further reduced and the detection accuracy is improved.

[0076] Please continue reading Figure 1 As shown, the step of determining the scanning granularity of the information of the browsed page includes:

[0077] If the number of abnormal logins in the unit detection period is greater than the preset first number and less than or equal to the preset second number, the number of privacy leakage methods is obtained;

[0078] Comparing the number of privacy leakage methods with a preset number;

[0079] If the number of the privacy leakage modes is greater than the preset number, it is determined that the comprehensiveness of the risk scan is lower than the allowable range, and the scanning granularity of the information on the browsed page is determined.

[0080] Please continue reading Figure 1 As shown, the scanning granularity of the determined browsing page information is inversely proportional to the difference between the number of the privacy leakage modes and the preset number.

[0081] Specifically, the number of privacy leakage methods is recorded as A, the preset number is recorded as A0, and the difference between the number of privacy leakage methods and the preset number is recorded as △A. △A=A-A0, and the difference between the preset number is recorded as △A0.

[0082] If △A≤△A0, the scanning granularity L of the information on the browsed page is adjusted using the preset first granularity adjustment coefficient β1;

[0083] If △A>△A0, the scanning granularity L of the information on the browsed page is adjusted using the preset second granularity adjustment coefficient β2;

[0084] Among them, 0<β1<β2<1, the scanning granularity of the information of the browsed page after adjustment is L'=L×βk, βk is the preset g-th granularity adjustment coefficient, and k is set to 1,2.

[0085] Furthermore, when the method of the present invention detects the risk of privacy leakage, since the change in the privacy data leakage mode leads to the inability to perform normal identification and thus causes the degree of privacy data leakage to increase, the scanning granularity of the information on the browsed page is reduced according to the number of privacy leakage modes, so that the scanning tool can analyze the privacy data more carefully and more easily discover potential vulnerabilities therein, thereby improving the accuracy of vulnerability detection, further achieving the reduction of privacy leakage risks and the improvement of detection accuracy.

[0086] Please continue reading Figure 1 As shown, the step of re-determining the number of feature comparison types in the database includes:

[0087] Comparing the time required for the privacy leakage alarm with a preset time;

[0088] If the time required for the privacy leakage alarm is longer than the preset time, it is determined that the real-time performance of risk detection is lower than the allowable range, and the number of feature comparison types in the database is redetermined based on the difference between the time required for the privacy leakage alarm and the preset time.

[0089] Specifically, the time required for the privacy leakage alarm is recorded as T, the preset time is recorded as T0, and the difference between the time required for the privacy leakage alarm and the preset time is recorded as △T. Set △T=T-T0, and the preset time difference is recorded as △T0.

[0090] The steps for re-determining the number of feature comparison types in the database are:

[0091] If △T≤△T0, the number V' of feature comparison types in the database is adjusted using the preset first number adjustment coefficient δ1;

[0092] If △T>△T0, the number V' of feature comparison types in the database is adjusted using the preset second number adjustment coefficient δ2;

[0093] Among them, 0<δ1<δ2<1 / 2, the number of feature comparison types in the re-determined database δg is the preset g-th order adjustment coefficient, and g=1, 2 is set.

[0094] The present invention also provides a privacy leakage risk detection device, comprising:

[0095] A data analysis module, used to periodically compare a certain amount of data on the browsing page with the privacy data feature points stored in the database to identify the privacy data, and to scan and detect a certain number of running processes of the browsing page to determine the privacy leakage risk information;

[0096] A comparison control module, connected to the data analysis unit, for determining the number of feature comparison types in the database according to an average error rate of several scanning detection processes, and re-determining the number of feature comparison types in the database according to the required time for a privacy leakage alarm under a first condition, wherein the first condition is when the number of feature comparison types in the database is determined;

[0097] A scanning validity monitoring module, which is respectively connected to the data analysis module and the comparison control module, is used to determine the backup frequency of privacy data based on the average error rate of the several scanning detection processes and the number of abnormal logins in a unit detection cycle, or to determine the scanning granularity of the information on the browsing page based on the number of abnormal logins in the unit detection cycle and the number of privacy leakage methods.

[0098] The present invention also provides a privacy leakage risk detection system, comprising a privacy leakage risk detection device and a control panel for displaying a privacy leakage alarm and privacy leakage risk information.

[0099] Example 1

[0100] In this embodiment 1, the average error rate P of several scanning detection processes is obtained to be 0.13, the preset first error rate P1 is 0.1, the preset second error rate P2 is 0.17, the difference between the error rate of several privacy leakage detections and the preset first error rate △P is 0.03, and the preset error rate difference △P0 is 0.05;

[0101] When ΔP≤ΔP0, the number of feature comparison types in the database V=3 is adjusted to V′=Ceil(7V / 5)=4.

[0102] This embodiment 1 increases the number of feature comparison types in the database, thereby improving the accuracy of data recognition, thereby further reducing the risk of privacy leakage and improving detection accuracy.

[0103] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A method for detecting privacy leakage risk, characterized in that: The following steps are involved: Periodically comparing a certain amount of data on the browsing page with the privacy data feature points stored in the database to identify the privacy data, and scanning and detecting a certain number of running processes on the browsing page to determine privacy leakage risk information; Determine the number of feature comparison types in the database based on the average error rate of several scanning detection processes, or make a preliminary judgment on the effectiveness of the scanning detection process based on the average error rate of several scanning detection processes and count the number of abnormal logins in a unit detection cycle; If the effectiveness of the scanning detection process is determined to be unsatisfactory based on the number of abnormal logins in the unit detection period, the backup frequency of the privacy data is determined, or the scanning granularity of the information on the browsed page is determined based on the number of abnormal logins in the unit detection period and the number of privacy leakage methods; Obtaining the time required for completing the privacy leakage alarm after the number of feature comparison types in the database is determined, and re-determining the number of feature comparison types in the database based on the time required for the privacy leakage alarm; The calculation formula for the average error rate of several scanning detection processes is: , Where P is the average error rate of several scanning detection processes, pj is the number of information leakages in the jth detection cycle, n is the number of detection cycles, n is a natural number greater than or equal to 1, and p is the number of scanning detections in one cycle; The step of determining the number of feature comparison types in the database comprises: Obtaining the error rate of several detection cycles and calculating the average error rate of several scanning detection processes; Comparing the average error rate of the plurality of scanning detection processes with a preset first error rate and a preset second error rate respectively; If the average error rate of the plurality of scanning detection processes is greater than the preset first error rate and less than or equal to the preset second error rate, it is determined that the stability of the privacy leakage detection is lower than the allowable range, and the number of feature comparison types in the database is determined; The number of feature comparison types in the database is determined by the difference between the average error rate of the plurality of scanning detection processes and the preset first error rate; The step of determining the backup frequency of the private data includes: If the average error rate of the plurality of scanning and detection processes is greater than the preset second error rate, it is preliminarily determined that the effectiveness of the scanning and detection process is lower than the allowable range, and the number of abnormal logins in the unit detection cycle is obtained; The number of abnormal logins in the unit detection period is compared with a preset first number and a preset second number respectively; If the number of abnormal logins in the unit detection cycle is greater than the preset second number, the effectiveness of the privacy leakage risk scan is secondarily determined to be lower than the allowable range, and the backup frequency of the privacy data is determined.

2. The method for detecting privacy leakage risk according to claim 1, characterized in that: The backup frequency of the privacy data is determined based on the difference between the number of abnormal logins in the unit detection period and the preset second number.

3. The method for detecting privacy leakage risk according to claim 2, characterized in that: The step of determining the scanning granularity of the information of the browsed page comprises: If the number of abnormal logins in the unit detection period is greater than the preset first number and less than or equal to the preset second number, the number of privacy leakage methods is obtained; Comparing the number of privacy leakage methods with a preset number; If the number of the privacy leakage modes is greater than the preset number, it is determined that the comprehensiveness of the risk scan is lower than the allowable range, and the scanning granularity of the information on the browsed page is determined.

4. The method for detecting privacy leakage risk according to claim 3, characterized in that: The determined scanning granularity of the information of the browsed page is inversely proportional to the difference between the number of the privacy leakage modes and the preset number.

5. The method for detecting privacy leakage risk according to claim 4, characterized in that: The step of re-determining the number of feature comparison types in the database comprises: Comparing the time required for the privacy leakage alarm with a preset time; If the time required for the privacy leakage alarm is longer than the preset time, it is determined that the real-time performance of risk detection is lower than the allowable range, and the number of feature comparison types in the database is redetermined based on the difference between the time required for the privacy leakage alarm and the preset time.

6. A detection device based on the privacy leakage risk detection method according to any one of claims 1 to 5, characterized in that: include, A data analysis module, used to periodically compare a certain amount of data on the browsing page with the privacy data feature points stored in the database to identify the privacy data, and to scan and detect a certain number of running processes of the browsing page to determine the privacy leakage risk information; A comparison control module, connected to the data analysis unit, for determining the number of feature comparison types in the database according to an average error rate of several scanning detection processes, and re-determining the number of feature comparison types in the database according to the required time for a privacy leakage alarm under a first condition, wherein the first condition is when the number of feature comparison types in the database is determined; A scanning validity monitoring module, which is respectively connected to the data analysis module and the comparison control module, is used to determine the backup frequency of privacy data based on the average error rate of the several scanning detection processes and the number of abnormal logins in a unit detection cycle, or to determine the scanning granularity of the information on the browsing page based on the number of abnormal logins in the unit detection cycle and the number of privacy leakage methods.

7. A detection system based on the privacy leakage risk detection method according to any one of claims 1 to 5, characterized in that: It comprises the privacy leakage risk detection device as claimed in claim 6 and a control panel for displaying privacy leakage alarm and privacy leakage risk information.