Analysis and evaluation system for password security

Abstract

The invention relates to the field of password security evaluation, in particular to an analysis and evaluation system for password security, which comprises an image storage library; the keyword matching unit is used for determining a keyword matching mode of the evidence image according to the type of the evidence image; the image selection unit is used for determining an image selection mode of the secret evaluation text according to a setting condition so as to select a target image; the risk judgment unit is used for determining an image risk value judgment mode according to the evidence image type; the desensitization processing unit is used for determining a desensitization mode of the target image according to the analysis condition; the auxiliary selection unit is used for determining a supplementary selection mode of the evidence image according to the image relevancy; the method can improve the integrity of the evaluation result while reducing the risk of information leakage.

Description

Technical Field

[0001] The present invention relates to the field of cryptographic security assessment, and particularly to an analysis and assessment system for cryptographic security. Background Art

[0002] When generating a cryptographic assessment report, cryptographic assessors can place cryptographic assessment-related evidence images in the report in the form of hyperlinks according to actual needs. However, currently, most assessors have full access rights to the evidence images, resulting in a risk of easy leakage of the evidence images. Therefore, how to provide adaptive access rights to the evidence images corresponding to the cryptographic assessment report on the basis of ensuring information security to improve the security of the cryptographic assessment process is a technical problem that needs to be solved urgently by those skilled in the art.

[0003] Chinese Patent Publication No. CN117993844A discloses a cryptographic application supervision method, device, medium, and electronic device. The method includes: using an intelligent solution recommendation algorithm to quickly match similar cases; business users preparing a cryptographic application solution according to the similar cases; business administrators evaluating the cryptographic application solution through a pre-generated self-assessment model to determine an initial assessment report; business administrators creating a review process corresponding to the cryptographic application solution; review users filling in review opinions on the cryptographic application solution and summarizing them into a review report; business administrators using OCR technology to parse and identify data in the review report, determining the core key data results of the review report, and determining whether the review report passes according to the core key data results. It can be seen that the above technical solution has the following problems: the selection range of evidence images is limited, and thus key image information related to the cryptographic assessment text cannot be fully displayed, resulting in incomplete assessment results, and there may be sensitive information in the cryptographic assessment report images, posing a risk of information leakage. Summary of the Invention

[0004] Therefore, the present invention provides an analysis and assessment system for cryptographic security to overcome the problems in the prior art that the selection range of evidence images is limited, and thus key image information related to the cryptographic assessment text cannot be fully displayed, resulting in incomplete assessment results, and there may be sensitive information in the cryptographic assessment report images, posing a risk of information leakage.

[0005] To achieve the above object, the present invention provides an analysis and assessment system for cryptographic security, including:

[0006] An image storage repository for storing evidence images;

[0007] A keyword matching unit connected to the image storage repository for determining the keyword matching method of the evidence images according to the evidence image type, and the keyword matching method is to determine the matching keywords according to the number of times of collocation use or to determine the matching keywords according to the feature matching degree;

[0008] An image selection unit, which is connected to the keyword matching unit, is used to determine the image selection method of the encrypted evaluation text according to the set conditions to select a target image. The image selection method is to select evidence images according to feature keywords or keyword matching degrees;

[0009] A risk determination unit, which is respectively connected to the keyword matching unit and the image selection unit, is used to determine the image risk value determination method according to the evidence image type. The image risk value determination method is to determine the image risk value according to the sensitive area area and the number of sensitive areas or to determine the image risk value according to the number of sensitive keywords;

[0010] A desensitization processing unit, which is respectively connected to the image selection unit and the risk determination unit, is used to determine the desensitization method of the target image according to the analysis conditions. The desensitization method is to perform blurring processing on the reference number of sensitive features in each feature combination or to perform blurring processing on all sensitive features;

[0011] An auxiliary selection unit, which is respectively connected to the image storage library, the image selection unit and the desensitization processing unit, is used to determine the supplementary selection method of the evidence image according to the image relevance. The supplementary selection method is to select supplementary images in the order of the feature correlation coefficient or the keyword matching coefficient from large to small.

[0012] Furthermore, the keyword matching unit responds to the evidence image type to determine the keyword matching method of the evidence image;

[0013] When the keyword matching unit responds that the evidence image type is a text evidence image, it determines that the keyword matching method is to determine the matching keyword according to the number of times of collocation use;

[0014] When the keyword matching unit responds that the evidence image type is a scene evidence image, it determines that the keyword matching method is to determine the matching keyword according to the feature matching degree;

[0015] The evidence image type includes a text evidence image and a scene evidence image.

[0016] Furthermore, the keyword matching unit determines the matching keyword according to the number of times of collocation use, including:

[0017] For a text evidence image, record the text evidence image as the target text evidence image, record the other text evidence images except the target text evidence image as the reference text evidence images, detect the corresponding similar images of the target text evidence image, and perform matching analysis on each similar image;

[0018] When performing matching analysis on a single homogeneous image, the homogeneous image is denoted as the reference homogeneous image, the same keywords in the target text evidence image and the reference homogeneous image are denoted as the reference same keywords, the other keywords in the target text evidence image except the reference keywords are denoted as the keywords to be analyzed, and the keywords with the number of collocation uses greater than the preset number of collocation uses in the uploaded data for a single keyword to be analyzed are denoted as collocation keywords;

[0019] All the keywords in the target text evidence image and the collocation keywords corresponding to each keyword to be analyzed are denoted as the matching keywords of the target text evidence image;

[0020] The homogeneous image is a reference text evidence image with the number of same keywords greater than the preset number of same keywords and the similarity of the same keyword distribution greater than the preset similarity of the same keyword distribution as the target text evidence image.

[0021] Further, the image selection unit responds to the set conditions to determine the image selection method for the encrypted evaluation text;

[0022] The set conditions to which the image selection unit responds are that the influence keyword ratio is greater than or equal to the preset influence keyword ratio or the influence factor is greater than or equal to the preset influence factor, and it is determined that the image selection method is to select evidence images according to the feature keywords;

[0023] The set conditions to which the image selection unit responds are that the influence keyword ratio is less than the preset influence keyword ratio and the influence factor is less than the preset influence factor, and it is determined that the image selection method is to select evidence images according to the keyword matching degree;

[0024] The feature keyword is a keyword in the influence keyword group with a sub-influence factor greater than the preset sub-influence factor.

[0025] Further, the image selection unit determines the sub-influence factor according to the disorder coefficient, where,

[0026] If the disorder coefficient is greater than or equal to the preset disorder coefficient, the sub-influence factor is determined according to the influence mean value;

[0027] If the disorder coefficient is less than the preset disorder coefficient, the sub-influence factor is determined according to the paragraph length and the number of associations.

[0028] Further, the risk determination unit responds to the evidence image type to determine the image risk value determination method;

[0029] For the scenario evidence image corresponding to the risk determination unit, the image risk value is determined according to the sensitive area area and the number of sensitive areas;

[0030] For the text evidence image corresponding to the risk determination unit, the image risk value is determined according to the number of sensitive keywords.

[0031] Further, the desensitization processing unit responds to the analysis condition to determine the desensitization method of the target image;

[0032] The analysis condition to which the desensitization processing unit responds is that the proportion of risk images is greater than or equal to the preset proportion of risk images or the mean value of sensitive feature distribution is greater than or equal to the preset mean value of sensitive feature distribution. It is determined that the desensitization method is to perform blurring processing on the sensitive features with the reference quantity in each feature combination;

[0033] The analysis condition to which the desensitization processing unit responds is that the proportion of risk images is less than the preset proportion of risk images and the mean value of sensitive feature distribution is less than the preset mean value of sensitive feature distribution. It is determined that the desensitization method is to perform blurring processing on all sensitive features.

[0034] Further, the desensitization method to which the desensitization processing unit responds is to perform blurring processing on the sensitive features with the reference quantity in each feature combination, where

[0035] When performing combined analysis on a single sensitive feature in a single evidence image, this sensitive feature is denoted as the target sensitive feature, the other sensitive features in this evidence image except the target sensitive feature are denoted as reference sensitive features, and the set of reference sensitive features with a feature correlation degree greater than the preset feature correlation degree with the target sensitive feature and the target sensitive feature is recorded into a feature combination;

[0036] And continue to perform combined analysis on the sensitive features not recorded in the feature combination until all sensitive features are recorded in the feature combination. Randomly select the sensitive features with the reference quantity in a single feature combination for blurring processing. The reference quantity has a positive correlation with the number of sensitive features corresponding to a single feature combination;

[0037] The sensitive features include sensitive regions and sensitive keywords.

[0038] Further, the desensitization processing unit determines the feature correlation degree according to the sensitive features;

[0039] If the sensitive feature is a sensitive keyword, the feature correlation degree is determined according to the collocation coefficient and the interval reference value;

[0040] If the sensitive feature is a sensitive region, the feature correlation degree is determined according to the device correlation degree.

[0041] Further, the auxiliary selection unit determines the supplementary selection method of the evidence image according to the image correlation degree;

[0042] If the image correlation degree is greater than or equal to the preset image correlation degree, the supplementary selection method is to select supplementary images in the order of the feature correlation coefficient from large to small;

[0043] If the image relevance is less than the preset image relevance, the supplementary selection method is to select supplementary images in the order of the keyword matching coefficients from large to small.

[0044] Compared with the prior art, the beneficial effects of the present invention are as follows. In the technical solution of the present invention, different keyword matching methods for evidence images are adaptively selected according to the evidence image type, so that the selection of the keyword matching method is more in line with the actual state of generating matching keywords, and can more accurately capture the key information in the evidence image, avoiding the problem that the subsequent recommended evidence images have a poor relevance to the secret evaluation text due to unreasonable setting of the matching keywords, ensuring that the recommended evidence images are closely related to the secret evaluation text, helping to improve the overall quality of the secret evaluation report, being able to comprehensively display the key image information related to the secret evaluation text, and improving the persuasiveness and credibility of the evaluation results.

[0045] Furthermore, in the present invention, the image selection method for the secret evaluation text is determined according to the set conditions. The set conditions effectively reflect the influence degree of the text evidence image on the keywords and the actual characteristics of the text evidence image. Then, different image selection methods are adaptively selected according to the set conditions, and the selection strategy can be automatically adjusted according to the specific characteristics of the text evidence image, so that the selected evidence images have a relatively high relevance to the secret evaluation text, thereby improving the flexibility and pertinence of the evidence image selection.

[0046] Furthermore, in the present invention, the distribution state of the same influencing keywords is effectively reflected by the disorder coefficient, and then the sub-influencing factors are determined according to the disorder coefficient, making the determination of the sub-influencing coefficients more in line with the actual distribution characteristics, improving the accuracy of the determination of the sub-influencing factors, being beneficial to subsequent selection of evidence images according to the characteristic keywords, and thus improving the accuracy of the evidence image selection.

[0047] Furthermore, in the present invention, the desensitization method of the target image is determined according to the analysis conditions. The analysis conditions effectively reflect the proportion of the risk images and the distribution of the sensitive features. Then, different desensitization methods are adaptively selected according to the analysis conditions, making the selection of the desensitization method more in line with the actual application scenario. By effectively desensitizing the sensitive information, the risk of data leakage can be reduced, and the security of the secret evaluation work can be improved.

[0048] Furthermore, in the present invention, the supplementary selection method of the evidence image is determined according to the image relevance. The image relevance effectively reflects the relevance of the selected target image. Then, different supplementary selection methods are adaptively selected according to the image relevance, so that the supplementary selection method can select evidence images with a relatively high relevance to the target image, enhancing the integrity of the evidence images in the secret evaluation report. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1Unit connection diagram of the analysis and evaluation system for password security of the present invention;

[0050] Figure 2 Flowchart of the present invention for determining the keyword matching method of evidence images according to the evidence image type;

[0051] Figure 3 Flowchart of the present invention for determining the image selection method of the cryptographic evaluation text according to the set conditions;

[0052] Figure 4 Flowchart of the present invention for determining the desensitization method of the target image according to the analysis conditions. Detailed implementation manners

[0053] In order to make the objectives and advantages of the present invention clearer, the present invention will be 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.

[0054] The preferred implementation manners of the present invention will be described below with reference to the accompanying drawings. Those skilled in the art should understand that these implementation manners are only used to explain the technical principles of the present invention and do not limit the protection scope of the present invention.

[0055] It should be noted that in the description of the present invention, the terms indicating directions or positional relationships such as "upper", "lower", "left", "right", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings. This is only for convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention.

[0056] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two elements. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0057] Please refer to Figures 1 to 4 As shown, the present invention provides an analysis and evaluation system for password security, including:

[0058] An image repository for storing evidence images;

[0059] A keyword matching unit, which is connected to the image repository and is used to determine the keyword matching method of the evidentiary image according to the evidentiary image type. The keyword matching method is to determine the matching keyword according to the number of times of collocation use or to determine the matching keyword according to the feature matching degree;

[0060] An image selection unit, which is connected to the keyword matching unit and is used to determine the image selection method of the encrypted evaluation text according to the set conditions to select the target image. The image selection method is to select the evidentiary image according to the feature keyword or the keyword matching degree;

[0061] A risk determination unit, which is respectively connected to the keyword matching unit and the image selection unit and is used to determine the image risk value determination method according to the evidentiary image type. The image risk value determination method is to determine the image risk value according to the sensitive area area and the number of sensitive areas or to determine the image risk value according to the number of sensitive keywords;

[0062] A desensitization processing unit, which is respectively connected to the image selection unit and the risk determination unit and is used to determine the desensitization method of the target image according to the analysis conditions. The desensitization method is to perform blurring processing on the reference number of sensitive features in each feature combination or to perform blurring processing on all sensitive features;

[0063] An auxiliary selection unit, which is respectively connected to the image repository, the image selection unit and the desensitization processing unit and is used to determine the supplementary selection method of the evidentiary image according to the image relevance. The supplementary selection method is to select the supplementary image in the order from large to small according to the feature correlation coefficient or the keyword matching coefficient.

[0064] Among them, the application scenario of the present invention is the recommendation of evidentiary images in the encrypted evaluation text generated during the evaluation process of password security. The encrypted evaluation text is the text after evaluating the security of the password. In the present invention, there are several historical records correspondingly set. Any historical record records at least one of the feature matching degree, the number of identical keywords, the similarity of the distribution of identical keywords, the influencing factor, the keyword matching degree, the sub-influencing factor, and the confusion coefficient in the historical process of evidentiary image recommendation, and each historical record corresponds to a qualified mark. The qualified mark records whether the stability detection process meets the user's requirements. The qualified mark can be manually recorded. It can be understood that the user can determine whether the stability detection process meets the requirements according to the self-set index. The self-set index can be, but is not limited to, the false recommendation rate, which will not be elaborated here. Among them, the false recommendation rate is the number of times of falsely recommending evidentiary images.

[0065] Specifically, the keyword matching unit responds to the evidentiary image type to determine the keyword matching method of the evidentiary image;

[0066] When the keyword matching unit responds that the evidence image type is a text evidence image, it determines that the keyword matching method is to determine the matching keyword according to the collocation usage times;

[0067] When the keyword matching unit responds that the evidence image type is a scene evidence image, it determines that the keyword matching method is to determine the matching keyword according to the feature matching degree;

[0068] The evidence image types include text evidence images and scene evidence images.

[0069] Among them, when determining the matching keyword according to the feature matching degree, the keyword in the uploaded data with a feature matching degree greater than the preset feature matching degree is selected as the matching keyword of the evidence image;

[0070] The evidence image types include text evidence images and scene evidence images. A text evidence image is an image in which text appears, and a scene evidence image is an image in which no text appears;

[0071] The confirmation method of the collocation usage times is as follows: for a single keyword to be analyzed, this keyword to be analyzed is recorded as the target keyword to be analyzed. The positions where the target keyword to be analyzed appears in the uploaded data are detected, and the adjacent keywords corresponding to the target keyword to be analyzed at different positions are detected. For a single adjacent keyword, this adjacent keyword is recorded as the target keyword, and the number of times the target keyword appears among the adjacent keywords corresponding to each target keyword to be analyzed in the uploaded data is recorded as the collocation usage times corresponding to the target keyword; for a single keyword, the adjacent keyword corresponding to this keyword is a keyword with a character interval less than the first preset character interval from this keyword; for any two keywords, the character interval is the number of characters between the two keywords, and the uploaded data is the text uploaded by the user to the password security detection and evaluation system;

[0072] The value of the first preset character interval can be determined by the user according to the actual application scenario. The higher the user's requirement for the relevance degree between the collocation keyword and the keyword to be analyzed, the smaller the value of the first preset character interval. A value of the first preset character interval is provided, and the first preset character interval is 4;

[0073] The method for confirming the feature matching degree is as follows: for a single scene evidence image, identify the names corresponding to each network device in the scene evidence image and record them as name keywords. For a single keyword in the uploaded data, record this keyword as the target keyword. The feature matching degree corresponding to the target keyword = 1 / the average value of the minimum character intervals between the target keyword and each name keyword in the uploaded data. The method for confirming the minimum character interval between the target keyword and a single name keyword in the uploaded data is as follows: record this name keyword as the target name keyword, record the target name keywords at different positions in the uploaded data as reference keywords, detect the character intervals between the target keyword and each reference keyword, and record the minimum value among the character intervals as the minimum character interval;

[0074] In the present invention, the network devices include servers, network devices, and storage devices. The network devices include, but are not limited to, switches, routers, and firewalls. The servers include, but are not limited to, disk arrays, tape libraries, and NAS. Users can identify the names corresponding to the network devices through machine vision and deep learning networks, which is content easily understood by those skilled in the art and will not be elaborated herein;

[0075] The value of the preset feature matching degree can be determined by the user according to the actual application scenario. The greater the matching degree of the matching keyword and the scene evidence image for the user, the greater the value of the preset feature matching degree. Provide a value of the preset feature matching degree, detect the historical records of keyword matching according to the feature matching degree, and record the average value of the feature matching degrees corresponding to the historical records that can meet the user's needs as the preset feature matching degree.

[0076] Specifically, the keyword matching unit determines the matching keyword according to the collocation usage times, including:

[0077] For a text evidence image, record this text evidence image as the target text evidence image, record the other text evidence images except the target text evidence image as the reference text evidence images, detect the corresponding similar images of the target text evidence image, and perform matching analysis on each similar image;

[0078] When performing matching analysis on a single similar image, record this similar image as the reference similar image, record the same keywords in the target text evidence image and the reference similar image as the reference same keywords, record the other keywords in the target text evidence image except the reference keywords as the keywords to be analyzed, and record the keyword whose collocation usage times with a single keyword to be analyzed in the uploaded data is greater than the preset collocation usage times as the collocation keyword;

[0079] Record all the keywords in the target text evidence image and the collocation keywords corresponding to each keyword to be analyzed as the matching keywords of the target text evidence image;

[0080] The similar images are reference text evidence images with the number of identical keywords greater than a preset number of identical keywords and the similarity of the distribution of identical keywords greater than a preset similarity of the distribution of identical keywords to the target text evidence image.

[0081] Among them, the confirmation methods for the number of identical keywords and the similarity of the distribution of identical keywords are as follows: for any two text evidence images, the number of identical keywords is the total number of identical keywords in the two text evidence images. Denote the larger value among the sub - coefficients corresponding to the two text evidence images as a1 and the smaller value as a2. The similarity of the distribution of identical keywords = 1 / (a1 - a2). The sub - coefficient corresponding to a single text evidence image is the average value of the reference distances corresponding to each identical keyword in this text evidence image. The reference distance corresponding to an identical keyword is the shortest distance from the central position of this identical keyword to the reference point, and the reference point is the center of the circumcircle of this text evidence image. The central position of a single keyword is the center of the circumcircle of the smallest rectangle that can contain this keyword.

[0082] The values of the preset number of paired uses, the preset number of identical keywords, and the preset similarity of the distribution of identical keywords can be determined by the user according to the actual application scenario. The higher the user's requirement for the relevance degree between the paired keywords and the keywords to be analyzed, the larger the value of the preset number of paired uses. Provide a value for the preset number of paired uses, and the preset number of paired uses is 5 times. The higher the user's requirement for the similarity degree of similar images, the larger the values of the preset number of identical keywords and the preset similarity of the distribution of identical keywords. Provide values for the preset number of identical keywords and the preset similarity of the distribution of identical keywords. Detect the historical records of determining similar images based on the number of identical keywords and the similarity of the distribution of identical keywords, and denote the average value of the number of identical keywords corresponding to the historical records that can meet the user's needs as the preset number of identical keywords, and denote the average value of the similarity of the distribution of identical keywords corresponding to the historical records that can meet the user's needs as the preset similarity of the distribution of identical keywords.

[0083] Specifically, the image selection unit responds to the set conditions to determine the image selection method for the encrypted evaluation text.

[0084] The set conditions to which the image selection unit responds are that the proportion of influencing keywords is greater than or equal to the preset proportion of influencing keywords or the influencing factor is greater than or equal to the preset influencing factor, and it is determined that the image selection method is to select evidence images according to the characteristic keywords.

[0085] The set conditions to which the image selection unit responds are that the proportion of influencing keywords is less than the preset proportion of influencing keywords and the influencing factor is less than the preset influencing factor, and it is determined that the image selection method is to select evidence images according to the keyword matching degree.

[0086] The feature keyword is a keyword in the impact keyword group where the sub-impact factor is greater than the preset sub-impact factor.

[0087] Among them, the setting conditions include a first setting condition and a second setting condition. The first setting condition is that the proportion of impact keywords is less than the preset proportion of impact keywords and the impact factor is less than the preset impact factor. The second setting condition is that the proportion of impact keywords is less than the preset proportion of impact keywords and the impact factor is less than the preset impact factor.

[0088] When selecting evidence images according to the feature keywords, the evidence images with a keyword matching degree greater than the preset keyword matching degree with the keywords of the text to be encrypted are used as the target images corresponding to the text to be encrypted.

[0089] When selecting evidence images according to the keyword matching degree, identify the feature keywords in the text to be encrypted, and use the evidence images with the feature keywords as the target images corresponding to the text to be encrypted.

[0090] The proportion of impact keywords = the number of impact keyword groups / (the number of keyword groups + the number of keywords that appear only once in the text to be encrypted). Impact keywords are keywords that appear more than the first preset number of times in the text to be encrypted. The set of keywords that appear more than once in the text to be encrypted is denoted as the keyword group. If the keyword in a keyword group is an impact keyword, then this keyword group is an impact keyword group. The impact factor is the average value of the sub-impact factors corresponding to each impact keyword group.

[0091] For the values of the first preset number of times, the preset proportion of impact keywords, and the preset impact factor, the user can determine them according to the actual application scenario. The smaller the value of the first preset number of times, the greater the user's need to determine the keyword as an impact keyword. Provide a value for the first preset number of times, which is 5 times. The smaller the values of the preset proportion of impact keywords and the preset impact factor, the greater the user's need to select evidence images according to the feature keywords. Provide values for the preset proportion of impact keywords and the preset impact factor. The preset proportion of impact keywords is 50%. Detect the historical records of selecting evidence images according to the feature keywords, and record the average value of the impact factors corresponding to the historical records that can meet the user's needs as the preset impact factor.

[0092] The method for confirming the keyword matching degree is as follows: for an evidence image, record this evidence image as the target evidence image, and detect whether the matching keywords corresponding to the target evidence image appear in the text to be encrypted. If the matching keywords appear in the text to be encrypted, they are recorded as target matching keywords. The keyword matching degree = the number of target matching keywords among the matching keywords corresponding to the target evidence image / the total number of matching keywords corresponding to the target evidence image.

[0093] The values of the preset keyword matching degree and the preset sub-influence factor can be determined by the user according to the actual application scenario. The greater the user's demand for improving the matching degree between the evidence image and the text of the cryptographic evaluation, the greater the values of the preset keyword matching degree and the preset sub-influence factor. A value of the preset keyword matching degree is provided. The historical records of selecting evidence images according to the keyword matching degree are detected, and the average value of the keyword matching degrees corresponding to the historical records that can meet the user's needs is recorded as the preset keyword matching degree. A value of the preset sub-influence factor is provided. The historical records of selecting evidence images according to the feature keywords are detected, and the average value of the sub-influence factors corresponding to the historical records that can meet the user's needs is recorded as the preset sub-influence factor.

[0094] Specifically, the image selection unit determines the sub-influence factor according to the disorder coefficient, where

[0095] if the disorder coefficient is greater than or equal to the preset disorder coefficient, the sub-influence factor is determined according to the influence mean value;

[0096] if the disorder coefficient is less than the preset disorder coefficient, the sub-influence factor is determined according to the paragraph length and the number of associations.

[0097] Among them, if the disorder coefficient is greater than or equal to the preset disorder coefficient, the sub-influence factor has a positive correlation with the influence mean value; if the disorder coefficient is less than the preset disorder coefficient, the sub-influence factor = paragraph length - number of associations;

[0098] The way to confirm the disorder coefficient is as follows: for a single impact keyword in a single impact keyword group, this impact keyword is denoted as the target impact keyword, and the other impact keywords in this impact keyword group except the target impact keyword are denoted as reference impact keywords. The average value of the shortest distances from the central position of the target impact keyword to the central positions of each reference impact keyword is denoted as the disorder coefficient corresponding to this impact keyword group;

[0099] The influence mean value is the average value of the influence thresholds corresponding to each impact keyword in a single impact keyword group. The influence threshold is the total number of associated keywords corresponding to a single impact keyword. The method for confirming the associated keywords corresponding to a single impact keyword is as follows: for a single impact keyword, this impact keyword is denoted as the target keyword, and the impact keywords with a character interval less than the second preset character interval from the target keyword are denoted as the associated keywords corresponding to the target keyword; the paragraph length is the number of characters between the first impact keyword and the last impact keyword in a single impact keyword group in the order of reading the text of the cryptographic evaluation from front to back, and the number of associations is the number of times the adjacent keyword that appears the most times among the adjacent keywords corresponding to each impact keyword in a single impact keyword group appears;

[0100] The values of the preset disorder coefficient and the second preset character interval can be determined by the user according to the actual application scenario. The smaller the value of the preset disorder coefficient, the greater the user's need to determine the sub-influence factor based on the influence mean. Provide a value for the preset disorder coefficient, detect the historical records of determining the sub-influence factor based on the influence mean, and record the average value of the disorder coefficients corresponding to the historical records that can meet the user's needs as the preset disorder coefficient. The greater the user's need for the effective degree of the provided associated keywords to affect the influence keyword, the smaller the value of the second preset character interval. Provide a value for the second preset character interval, and the value of the second preset character interval is 10 characters.

[0101] Specifically, the risk determination unit responds to the evidence image type to determine the image risk value determination method;

[0102] The risk determination unit corresponds to the scenario evidence image and determines the image risk value according to the sensitive area area and the number of sensitive areas;

[0103] The risk determination unit corresponds to the text evidence image and determines the image risk value according to the number of sensitive keywords.

[0104] Among them, for a single scenario evidence image, the image risk value = sensitive area area + number of sensitive areas;

[0105] For the text evidence image, the image risk value has a positive correlation with the number of sensitive keywords;

[0106] The sensitive area area is the sum of the areas of each sensitive area in a single scenario evidence image. The user can determine the area of each sensitive area through OpenCV, which will not be elaborated here. The number of sensitive areas is the total number of each sensitive area in a single scenario evidence image; the sensitive area is the area where each network device is located in the scenario evidence image;

[0107] The number of sensitive keywords is the total number of sensitive keywords in a single text evidence image. The sensitive keyword is a keyword whose occurrence times in the uploaded data are greater than the second preset occurrence times. The value of the second preset occurrence times can be determined by the user according to the actual application scenario. The greater the user's need for the sensitivity determination of the sensitive keyword, the smaller the value of the second preset occurrence times. Provide a value for the second preset occurrence times, and the second preset occurrence times is 15 times.

[0108] Specifically, the desensitization processing unit responds to the analysis condition to determine the desensitization method of the target image;

[0109] The analysis condition to which the desensitization processing unit responds is that the proportion of risk images is greater than or equal to the preset risk image proportion or the mean value of the sensitive feature distribution is greater than or equal to the preset sensitive feature distribution mean value. It is determined that the desensitization method is to perform blurring processing on the sensitive features with the reference quantity in each feature combination;

[0110] The analysis condition for the desensitization processing unit to respond is that the proportion of risk images is less than the preset proportion of risk images and the mean value of the sensitive feature distribution is less than the preset mean value of the sensitive feature distribution, and it is determined that the desensitization method is to perform blurring processing on all sensitive features.

[0111] Among them, the analysis conditions include a first analysis condition and a second analysis condition. The first analysis condition is that the proportion of risk images is greater than or equal to the preset proportion of risk images or the mean value of the sensitive feature distribution is greater than or equal to the preset mean value of the sensitive feature distribution. The second analysis condition is that the proportion of risk images is less than the preset proportion of risk images and the mean value of the sensitive feature distribution is less than the preset mean value of the sensitive feature distribution;

[0112] The proportion of risk images = the total number of risk evidence images / the number of all evidence images. A risk image is an evidence image with an image risk value greater than the preset image risk value.

[0113] The mean value of the sensitive feature distribution is the average of the sensitive feature distribution coefficients corresponding to each evidence image. The method for confirming the sensitive feature distribution coefficient is as follows: for a single evidence image, this evidence image is recorded as the target evidence image, and the sensitive feature distribution coefficient corresponding to the target evidence image is the average of the sensitive distances corresponding to each sensitive feature in the target evidence image. For a single sensitive feature, this sensitive feature is recorded as the target sensitive feature, and the other sensitive features in the target evidence image except the target sensitive feature are recorded as reference features. The minimum value among the shortest distances from the center position of the target sensitive feature to the center positions of each reference sensitive feature is recorded as the sensitive distance corresponding to the target sensitive feature; if the sensitive feature is a sensitive area, the center position of the sensitive feature is the center of the circumscribed circle of a single sensitive area. If the sensitive feature is a keyword, the center position of the sensitive feature is the center of the circumscribed circle of the smallest rectangle that can contain a single keyword;

[0114] The values of the preset proportion of risk images, the preset sensitive feature distribution coefficient, and the preset image risk value can be determined by the user according to the actual application scenario. The larger the values of the preset proportion of risk images and the preset sensitive feature distribution coefficient, the greater the user's demand for blurring processing of all sensitive features. Provide a value for the preset proportion of risk images and the preset sensitive feature distribution coefficient. The preset proportion of risk images is 50%. Detect the historical records of blurring processing of the sensitive features with the reference quantity in each feature combination, and record the average value of the sensitive feature distribution coefficients corresponding to the historical records that can meet the user's needs as the preset sensitive feature distribution coefficient;

[0115] When performing blurring processing on sensitive features, a blurring algorithm is used for processing, which can make the sensitive features become blurred and not easily recognizable. The blurring algorithm includes but is not limited to fuzzy logic and fuzzy set theory, and the user can select according to actual needs, which will not be elaborated here.

[0116] Specifically, the desensitization method responded by the desensitization processing unit is to perform blurring processing on the sensitive features with the reference quantity in each feature combination, where,

[0117] When performing combined analysis on a single sensitive feature in a single evidence image, the sensitive feature is denoted as the target sensitive feature, the other sensitive features in the evidence image except the target sensitive feature are denoted as reference sensitive features, and the set of reference sensitive features whose feature correlation degree with the target sensitive feature is greater than the preset feature correlation degree and the target sensitive feature are recorded into a feature combination;

[0118] And continue to perform combined analysis on the sensitive features not recorded into the feature combination until all sensitive features are recorded into the feature combination, randomly select the sensitive features with the reference quantity in a single feature combination for blurring processing, and the reference quantity has a positive correlation with the number of sensitive features corresponding to a single feature combination;

[0119] The sensitive features include sensitive regions and sensitive keywords.

[0120] Among them, the value of the preset feature correlation degree can be determined by the user according to the actual application scenario. The greater the user's demand for the correlation degree of each sensitive feature in the feature combination, the greater the value of the preset feature correlation degree. Provide a value of the preset feature correlation degree, detect the historical records of selecting the sensitive features with the reference quantity in each feature combination for blurring processing, and record the average value of the feature correlation degrees corresponding to the historical records that can meet the user's needs as the preset feature correlation degree.

[0121] Specifically, the desensitization processing unit determines the feature correlation degree according to the sensitive features;

[0122] If the sensitive feature is a sensitive keyword, determine the feature correlation degree according to the collocation coefficient and the interval reference value;

[0123] If the sensitive feature is a sensitive region, determine the feature correlation degree according to the device correlation degree.

[0124] Among them, for sensitive keywords, the feature correlation degree = collocation coefficient - interval reference value; for sensitive regions, the feature correlation degree has a positive correlation with the device correlation degree; the confirmation method of the collocation coefficient is that for two sensitive keywords in a single text evidence image, they are respectively denoted as the first keyword and the second keyword in the order of reading from first to last, detect the position where the first keyword appears in the uploaded data, and detect the adjacent keywords corresponding to the target sensitive keyword at different positions, and record the number of times the second keyword appears among the adjacent keywords as the collocation coefficient corresponding to the two sensitive keywords; the interval reference value is the number of characters between the first keyword and the second keyword in a single text evidence image; the device correlation degree = 1 / the shortest distance between the central positions of the two sensitive regions.

[0125] Specifically, the auxiliary selection unit determines the supplementary selection method of the evidence image according to the image relevance;

[0126] If the image relevance is greater than or equal to the preset image relevance, the supplementary selection method is to select supplementary images in descending order of the feature correlation coefficient;

[0127] If the image relevance is less than the preset image relevance, the supplementary selection method is to select supplementary images in descending order of the keyword matching coefficient.

[0128] Wherein, the evidence images that are not selected as target images are recorded as reference images. When selecting supplementary images in descending order of the feature correlation coefficient and when selecting supplementary images in descending order of the keyword matching coefficient, the reference images are selected as supplementary images, and the number of supplementary images selected can be determined by the user according to actual needs, without specific limitation;

[0129] Image relevance = feature correlation degree - Smin / Smax, where Smin and Smax are respectively the smaller value and the larger value of the number of text evidence images and scene evidence images in the selected target images. The maximum value of the feature correlation degrees in the selected target images is denoted as m1, and the minimum value is denoted as m2. Feature correlation degree = 1 - (m1 - m2) / m1; The method for confirming the feature correlation coefficient is that for a single reference image, the feature correlation coefficient corresponding to this reference image = 1 / |the feature correlation degree corresponding to this reference image - the average value of the feature correlation degrees corresponding to each target image|;

[0130] The method for confirming the keyword matching coefficient is that the matching keywords corresponding to the target images are denoted as analysis keywords. For a single reference image, the keyword matching coefficient corresponding to this reference image = the number of matching keywords in the matching keywords corresponding to this reference image that are the same as the analysis keywords / the total number of the matching keywords corresponding to this reference image;

[0131] The value of the preset image relevance can be determined by the user according to the actual application scenario. The smaller the value of the preset image relevance, the greater the user's demand for selecting supplementary images in descending order of the feature correlation coefficient. Provide a value of the preset image relevance, detect the historical records of selecting supplementary images in descending order of the feature correlation coefficient, and denote the average value of the image relevance corresponding to the historical records that can meet the user's needs as the preset image relevance.

[0132] So far, the technical solution of the present invention has 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.

[0133] The above are only the preferred embodiments of the present invention and are not used to limit the present invention; for those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A cryptographic security analysis and evaluation system, characterized in that: include: An image repository for storing evidence images; A keyword matching unit connected to the image storage library is used to determine a keyword matching method for the evidence image according to the type of the evidence image, wherein the keyword matching method is to determine the matching keyword according to the number of times the combination is used or to determine the matching keyword according to the feature matching degree; An image selection unit, which is connected to the keyword matching unit, and is used to determine an image selection method for the secret review text according to the set conditions to select a target image, wherein the image selection method is to select an evidence image according to a characteristic keyword or a keyword matching degree; a risk determination unit, which is connected to the keyword matching unit and the image selection unit respectively, and is used to determine an image risk value determination method according to the type of evidence image, wherein the image risk value determination method is to determine the image risk value according to the area of ​​the sensitive region and the number of sensitive regions or to determine the image risk value according to the number of sensitive keywords; a desensitization processing unit, which is connected to the image selection unit and the risk determination unit respectively, and is used to determine a desensitization method of the target image according to the analysis conditions, wherein the desensitization method is to select a reference number of sensitive features in each feature combination for fuzzy processing or to perform fuzzy processing on all sensitive features; An auxiliary selection unit is respectively connected to the image storage library, the image selection unit and the desensitization processing unit, and is used to determine a supplementary selection method for the evidence image according to the image relevance. The supplementary selection method is to select supplementary images in descending order of feature association coefficients or keyword matching coefficients.

2. The analysis and evaluation system for password security according to claim 1, characterized in that: The keyword matching unit responds to the type of the evidence image to determine a keyword matching method for the evidence image; The keyword matching unit responds that the evidence image type is a text evidence image, and determines the keyword matching method as determining the matching keyword according to the number of times the combination is used; The keyword matching unit responds that the type of the evidence image is a scene evidence image, and determines the keyword matching method as determining the matching keyword according to the feature matching degree; The evidence image types include text evidence images and scene evidence images.

3. The analysis and evaluation system for password security according to claim 2, characterized in that: The keyword matching unit determines the matching keyword according to the number of times the combination is used, including: For a text evidence image, the text evidence image is recorded as a target text evidence image, and other text evidence images except the target text evidence image are recorded as reference text evidence images, and each similar image corresponding to the target text evidence image is detected, and matching analysis is performed on each similar image; When performing matching analysis on a single image of the same type, the image of the same type is recorded as a reference image of the same type, the same keywords in the target text evidence image and the reference image of the same type are recorded as reference same keywords, the other keywords in the target text evidence image other than the reference keywords are recorded as keywords to be analyzed, and the keywords in the uploaded data that are used in combination with the single keyword to be analyzed more than the preset number of times are recorded as combination keywords; Each keyword in the target text evidence image and the collocation keyword corresponding to each keyword to be analyzed are recorded as the matching keyword of the target text evidence image; The similar image is a reference text evidence image having a greater number of identical keywords than a preset number of identical keywords and a greater similarity in distribution of identical keywords than a preset similarity in distribution of identical keywords as the target text evidence image.

4. The analysis and evaluation system for password security according to claim 3, characterized in that: The image selection unit responds to the set conditions to determine the image selection method of the secret review text; The setting condition of the image selection unit response is that the proportion of the influencing keywords is greater than or equal to the preset proportion of the influencing keywords or the influencing factor is greater than or equal to the preset influencing factor, and the image selection method is to select the evidence image according to the characteristic keywords; The setting condition of the image selection unit response is that the proportion of the influencing keywords is less than the preset proportion of the influencing keywords and the influencing factor is less than the preset influencing factor, and the image selection method is determined to select the evidence image according to the keyword matching degree; The characteristic keyword is a keyword in the influence keyword group whose sub-influence factor is greater than a preset sub-influence factor.

5. The analysis and evaluation system for password security according to claim 4, characterized in that: The image selection unit determines the sub-influence factor according to the disorder coefficient, wherein: If the disorder coefficient is greater than or equal to the preset disorder coefficient, the sub-influence factor is determined according to the influence mean; If the disorder coefficient is less than the preset disorder coefficient, the sub-influence factor is determined according to the paragraph length and the number of associations.

6. The analysis and evaluation system for password security according to claim 4, characterized in that: The risk determination unit responds to the evidence image type to determine the image risk value determination method; The risk determination unit corresponds to the scene evidence image and determines the image risk value according to the area and number of sensitive areas; The risk determination unit corresponds to the text evidence image and determines the image risk value according to the number of sensitive keywords.

7. The analysis and evaluation system for password security according to claim 6, characterized in that: The desensitization processing unit responds to the analysis conditions to determine a desensitization method for the target image; The analysis condition for the response of the desensitization processing unit is that the proportion of risk images is greater than or equal to the preset proportion of risk images or the mean value of the sensitive feature distribution is greater than or equal to the preset mean value of the sensitive feature distribution, and the desensitization method is to select a reference number of sensitive features in each feature combination for fuzzy processing; The analysis conditions for the response of the desensitization processing unit are that the proportion of risk images is less than the preset proportion of risk images and the mean value of the sensitive feature distribution is less than the preset mean value of the sensitive feature distribution, and the desensitization method is determined to be fuzzy processing for all sensitive features.

8. The analysis and evaluation system for password security according to claim 7, characterized in that: The desensitization method of the desensitization processing unit response is to select a reference number of sensitive features in each feature combination for fuzzy processing, wherein: When performing combined analysis on a single sensitive feature in a single evidence image, the sensitive feature is recorded as a target sensitive feature, and other sensitive features in the evidence image except the target sensitive feature are recorded as reference sensitive features, and the set of the reference sensitive features and the target sensitive features whose feature correlation with the target sensitive feature is greater than the preset feature correlation is recorded as a feature combination; Continue to perform combined analysis on sensitive features that are not recorded in the feature combination until all sensitive features are recorded in the feature combination, randomly select a reference number of sensitive features in a single feature combination for fuzzy processing, and the reference number is positively correlated with the number of sensitive features corresponding to the single feature combination; The sensitive features include sensitive areas and sensitive keywords.

9. The analysis and evaluation system for password security according to claim 8, characterized in that: The desensitization processing unit determines the feature correlation degree according to the sensitive features; If the sensitive feature is a sensitive keyword, the feature relevance is determined based on the matching coefficient and the interval reference value; If the sensitive feature is a sensitive area, the feature association is determined based on the device association.

10. The analysis and evaluation system for password security according to claim 9, characterized in that: The auxiliary selection unit determines a supplementary selection method of the evidence image according to the image relevance; If the image correlation is greater than or equal to the preset image correlation, the supplementary selection method is to select supplementary images in descending order of feature correlation coefficients; If the image relevance is less than the preset image relevance, the supplementary selection method is to select supplementary images in descending order of keyword matching coefficients.

Images