File identification feature determination method and device, equipment and storage medium

By obtaining static information of application files, determining single features, multiple features and fuzzy features, and generating identification features of application files, it solves the problem of high false alarm rates and missed rates caused by single application file identification features in the prior art. The problem has been more accurate.

CN119046937APending Publication Date: 2024-11-29BEIJING QIHOOD TECHNOLOGY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202310622076.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-05-29
Publication Date
2024-11-29

AI Technical Summary

Technical Problem

In the prior art, the application file identification characteristics are single, resulting in a high recognition false alarm rate and missed alarm rate.

Method used

By obtaining static information of application files, single features, multiple features and fuzzy features are determined, and identification features of application files are generated based on these features to reduce the recognition false alarm rate and missed alarm rate.

Benefits of technology

It improves the diversity of application file identification characteristics, reduces the recognition false alarm rate and missed alarm rate, and provides more accurate application file identification.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119046937A_ABST
    Figure CN119046937A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of security detection, and discloses a file identification feature determination method and device, equipment and a storage medium, and the method comprises the steps: obtaining static information of an application program file; determining a single feature, multiple features and fuzzy features according to the static information; generating application program file identification features according to the single features, the multiple features and the fuzzy features; according to the mode, after the static information of the application program file is recognized, the single feature, the multiple features and the fuzzy features are determined according to the static information, and then the multi-dimensional application program file recognition features are generated based on the single feature, the multiple features and the fuzzy features, so that the diversity of the obtained application program file recognition features can be improved; and more features are provided for subsequent identification of the application program, so that the false alarm rate and the missing report rate of identification are reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of security detection technology, and in particular to a method, device, equipment and storage medium for determining file identification features. Background Art

[0002] The identification of application files mainly involves identifying and extracting the basic information of the application files themselves. A common method is to perform basic analysis on the application files and then obtain the corresponding features based on the analysis results. However, the features determined by the above method are single and easy to be modified and redefined, such as names, version numbers, etc., which ultimately results in high false positive and false negative rates in application file identification.

[0003] The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of the present invention is to provide a method, device, equipment and storage medium for determining file identification features, aiming to solve the technical problem that the prior art obtains a single application file identification feature, resulting in a high false alarm rate and missed alarm rate in application file identification.

[0005] To achieve the above object, the present invention provides a method for determining a file identification feature, the method comprising the following steps:

[0006] Get static information of application files;

[0007] Determine a single feature, multiple features, and fuzzy features based on the static information;

[0008] An application file identification feature is generated according to the single feature, multiple features and fuzzy features.

[0009] Optionally, obtaining static information of the application file includes:

[0010] Get the download network address of the application file;

[0011] crawling the application file according to the download network address;

[0012] The application file is identified according to the static information identification strategy to obtain static information of the application file.

[0013] Optionally, obtaining a download network address of the application file includes:

[0014] Obtain file download information from application markets, web pages, and third-party channels;

[0015] When the file download information of the application market contains download information of the application file, the file download information of the web page contains download information of the application file, or the file download information of the third-party channel contains download information of the application file, the download network address of the application file is determined.

[0016] Optionally, determining a download network address of the application file includes:

[0017] Searching for the file download information containing the download information of the application file to obtain the application file download information;

[0018] The application file download information is identified to obtain a download network address of the application file.

[0019] Optionally, the identifying the application file according to the static information identification strategy to obtain the static information of the application file includes:

[0020] Performing resource analysis on the application file to obtain a resource analysis result;

[0021] Performing decompilation analysis on the application file to obtain a decompilation analysis result;

[0022] The resource analysis result and the decompilation analysis result are identified according to the static information identification strategy to obtain the static information of the application file.

[0023] Optionally, determining a single feature, multiple features, and fuzzy features according to the static information includes:

[0024] Extracting the static information;

[0025] Classify the extracted static information to obtain multi-category static information;

[0026] Single features, multiple features and fuzzy features are determined according to the multi-category static information.

[0027] Optionally, determining a single feature, multiple features, and fuzzy features according to the multi-category static information includes:

[0028] Obtaining attribute static information and fuzzy hash static information according to the multi-category static information;

[0029] Get the icon MD5 of the application file;

[0030] Determine a single static information according to the attribute static information and the icon MD5, and determine a single feature according to the single static information;

[0031] Combining a plurality of the attribute static information, and determining multiple features according to the combined multiple attribute static information;

[0032] A fuzzy feature is determined according to the fuzzy hash static information.

[0033] Optionally, generating the application file identification feature according to the single feature, multiple features and fuzzy features includes:

[0034] Obtaining the importance of the single feature, multiple features, and fuzzy features for identifying the application file;

[0035] Scoring the single feature, multiple features and fuzzy features respectively according to the importance;

[0036] Marking the single feature, multiple features and fuzzy features respectively according to the scoring scores;

[0037] Summarize the single feature after labeling and the score of the single feature, the multiple features after labeling and the score of the multiple features, and the fuzzy features after labeling and the score of the fuzzy features to obtain a label feature score data set;

[0038] The marker feature scoring data set is written into a target database for storing marker features and feature scoring scores, and an application file identification feature is generated according to the target database.

[0039] Optionally, after generating the application file identification feature according to the single feature, multiple features and fuzzy features, the method further includes:

[0040] Identify application file identification features through an application file identification engine;

[0041] It is determined whether the application file is a preset application file according to the recognition result.

[0042] Optionally, after determining whether the application file is a preset application file according to the recognition result, the method further includes:

[0043] When the application file is determined to be a preset application file according to the recognition result, marking the application file by using a preset pseudo label;

[0044] Categorize the marked application files.

[0045] In addition, to achieve the above-mentioned purpose, the present invention also proposes a file identification feature determination device, the file identification feature determination device comprising:

[0046] The acquisition module is used to obtain static information of application files;

[0047] A determination module, used to determine a single feature, multiple features and fuzzy features according to the static information;

[0048] A generation module is used to generate application file identification features based on the single feature, multiple features and fuzzy features.

[0049] Optionally, the acquisition module is further used to acquire a download network address of the application file; download the application file according to the download network address; identify the application file according to a static information identification strategy to obtain static information of the application file.

[0050] Optionally, the acquisition module is also used to obtain file download information from an application market, file download information from a web page, and file download information from a third-party channel; when there is download information of the application file in the file download information of the application market, or there is download information of the application file in the file download information of the web page, or there is download information of the application file in the file download information of a third-party channel, determine the download network address of the application file.

[0051] Optionally, the acquisition module is also used to perform resource analysis on the application file to obtain resource analysis results; perform decompilation analysis on the application file to obtain decompilation analysis results; identify the resource analysis results and decompilation analysis results according to a static information identification strategy to obtain static information of the application file.

[0052] Optionally, the determination module is further used to extract the static information; classify the extracted static information to obtain multi-category static information; and determine single features, multiple features and fuzzy features based on the multi-category static information.

[0053] Optionally, the determination module is also used to obtain attribute feature information and fuzzy hash feature information based on the multi-category feature information; obtain the icon MD5 of the application file; determine a single feature based on the attribute feature information and the icon MD5; combine several of the attribute feature information and determine multiple features based on the combination result; determine the fuzzy feature based on the fuzzy hash feature information.

[0054] Optionally, the generation module is also used to obtain the importance of the single feature, multiple features and fuzzy features for identifying the application file; score the single feature, multiple features and fuzzy features according to the importance; mark the single feature, multiple features and fuzzy features according to the scoring scores; summarize the marked single feature and the scoring scores of the single feature, the marked multiple features and the scoring scores of the multiple features, the marked fuzzy features and the scoring scores of the fuzzy features to obtain a marked feature scoring data set; write the marked feature scoring data set to a target database for storing marked features and feature scoring scores, and generate application file identification features based on the target database.

[0055] Optionally, the generating module is further configured to identify application file identification features through an application file identification engine; and determine whether the application file is a preset application file according to the identification result.

[0056] In addition, to achieve the above-mentioned purpose, the present invention also proposes a file identification feature determination device, which includes: a memory, a processor, and a file identification feature determination program stored in the memory and executable on the processor, and the file identification feature determination program is configured to implement the file identification feature determination method described above.

[0057] In addition, to achieve the above-mentioned purpose, the present invention also proposes a storage medium, on which a file identification feature determination program is stored, and when the file identification feature determination program is executed by a processor, the file identification feature determination method as described above is implemented.

[0058] The file identification feature determination method proposed in the present invention obtains static information of the application file; determines a single feature, multiple features and fuzzy features based on the static information; generates application file identification features based on the single feature, multiple features and fuzzy features; through the above method, after identifying the static information of the application file, determines a single feature, multiple features and fuzzy features based on the static information, and then generates multi-dimensional application file identification features based on the single feature, multiple features and fuzzy features, thereby improving the diversity of application file identification features, providing more features for subsequent identification of applications, and thereby reducing the false alarm rate and missed alarm rate of identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 It is a structural diagram of a device for determining file identification characteristics in a hardware operating environment involved in an embodiment of the present invention;

[0060] Figure 2It is a flowchart of a first embodiment of a method for determining a file identification feature of the present invention;

[0061] Figure 3 It is a schematic diagram of the overall flow of an embodiment of a method for determining a file identification feature of the present invention;

[0062] Figure 4 A schematic diagram of a flow chart of a second embodiment of a method for determining a file identification feature according to the present invention;

[0063] Figure 5 A schematic diagram of a flow chart of a third embodiment of a method for determining a file identification feature according to the present invention;

[0064] Figure 6 This is a functional module diagram of the first embodiment of the device for determining file identification features of the present invention.

[0065] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0066] 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.

[0067] Reference Figure 1 , Figure 1 A schematic diagram of a device structure for determining file identification features of a hardware operating environment involved in an embodiment of the present invention.

[0068] like Figure 1 As shown, the file identification feature determination device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wireless-Fidelity, Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM) memory, or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0069] Those skilled in the art will understand that Figure 1The structure shown in the figure does not constitute a limitation on the device for determining document identification characteristics, and may include more or less components than those shown in the figure, or combine certain components, or arrange the components differently.

[0070] like Figure 1 As shown, the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and a file identification feature determination program.

[0071] exist Figure 1 In the file identification feature determination device shown, the network interface 1004 is mainly used for data communication with the network integration platform workstation; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the file identification feature determination device of the present invention can be set in the file identification feature determination device, and the file identification feature determination device calls the file identification feature determination program stored in the memory 1005 through the processor 1001, and executes the file identification feature determination method provided by the embodiment of the present invention.

[0072] Based on the above hardware structure, an embodiment of a method for determining file identification features of the present invention is proposed.

[0073] Reference Figure 2 , Figure 2 It is a flowchart of the first embodiment of the method for determining file identification features of the present invention.

[0074] In a first embodiment, the method for determining the file identification feature comprises the following steps:

[0075] Step S10, obtaining static information of the application file.

[0076] It should be noted that the executor of this embodiment is a file recognition feature determination device, and may also be other devices that can achieve the same or similar functions, such as a feature determination controller, etc. This embodiment does not limit this. In this embodiment, the feature determination controller is taken as an example for explanation.

[0077] It should be understood that the application file may be an Android Package (APK) file, and the static information of the application file is obtained by identifying the application file, and the static information includes but is not limited to file size, package name, version number, certificate information, etc.

[0078] Step S20, determining a single feature, multiple features and fuzzy features according to the static information.

[0079] It can be understood that a single feature refers to the feature of a single application file, which is obtained by identifying static information, including but not limited to file size, package name, version number, etc. Multiple features refer to the features of multiple application files, which include but are not limited to icon + package name, package name + download network address, etc. Fuzzy features refer to the fuzzy hash features of application files, which include but are not limited to icon fuzzy hash features, file fuzzy hash features, etc.

[0080] Step S30, generating application file identification features according to the single feature, multiple features and fuzzy features.

[0081] It should be understood that the application file identification feature refers to an identification feature that accurately identifies whether an application file is a preset application file, and the application file identification feature is generated by a single feature, multiple features, and fuzzy features.

[0082] Further, step S30 includes: obtaining the importance of the single feature, multiple features and fuzzy features for identifying the application file; scoring the single feature, multiple features and fuzzy features according to the importance; marking the single feature, multiple features and fuzzy features according to the scoring scores; summarizing the marked single feature and the scoring scores of the single feature, the marked multiple features and the scoring scores of the multiple features, the marked fuzzy features and the scoring scores of the fuzzy features to obtain a marked feature scoring data set; writing the marked feature scoring data set to a target database for storing marked features and feature scoring scores, and generating application file identification features based on the target database.

[0083] It can be understood that the importance refers to the importance of a single feature, multiple features and fuzzy features for accurately identifying whether an application file is a preset application file. After determining the importance, the single feature, multiple features and fuzzy features are scored according to the importance, that is, the higher the importance, the higher the feature score. Then, the single feature, multiple features and fuzzy features are marked according to the score. For example, the higher the score, the higher the order of the marked feature. For example, the score of the fuzzy feature is A, the score of the single feature is B, and the score of the multiple features is C, and A>C>B, then the fuzzy feature is marked. The feature mark is the first, the multi-feature mark is the second, and the single feature mark is the third. Then the marked single feature and the single feature's scoring score, the marked multi-feature and the multi-feature's scoring score, the marked fuzzy feature and the fuzzy feature's scoring score are summarized to form a marked feature scoring data set, and then the marked feature scoring data set is written to the target database, which refers to the database used to mark features and feature scoring scores. After writing is completed, the target database has stored all the marked features, and then the application file recognition features are generated according to the target database, and then the feature recognition and analysis business process is carried out.

[0084] Furthermore, after step S30, the method further includes: identifying the application file identification feature by using an application file identification engine; and determining whether the application file is a preset application file according to the identification result.

[0085] It can be understood that the preset application file can be a counterfeit application file. The application file identification engine refers to a device used to accurately identify whether an application file is a preset application file. After obtaining the application file identification feature, the application file identification feature is identified by the application file identification engine, and then it is determined whether the application file is a preset application file based on the identification result.

[0086] Furthermore, after determining whether the application file is a preset application file according to the recognition result, the method further includes: when the application file is determined to be a preset application file according to the recognition result, marking the application file with a preset pseudo-label; and classifying the marked application file.

[0087] It should be understood that the preset pseudo-label refers to a label used to mark counterfeit application files. After obtaining the identification result, it is determined whether the application file is a preset application file based on the identification result. If so, it indicates that the application file is counterfeit. At this time, the preset pseudo-label is used to mark the application file, and then the marked application file is classified.

[0088] Understandably, reference Figure 3 , Figure 3 The figure is a schematic diagram of the overall process, which is as follows: the download network address of the application file is determined through the file download information of the application market, the file download information of the web page, and the file download information of the third-party channel, and then the application file is crawled out through the download network address, and then the resource analysis and decompilation analysis are performed on the application file respectively, and then the resource analysis results and the compilation analysis results are identified through the static information identification strategy to obtain the static information of the application file. The static information at this time includes attribute static information and fuzzy hash static information, and then a single feature and multiple features are determined according to the attribute static information, and a fuzzy hash feature is determined according to the fuzzy hash static information, and then the single feature, multiple features and fuzzy hash features are marked according to the importance, and the marked single feature and the score of the single feature, the marked multiple features and the score of the multiple features, the marked fuzzy features and the score of the fuzzy features are summarized as a marked feature scoring data set, and then the marked feature scoring data set is written to the target database for storing the marked features and feature scoring scores, and then the application file identification features are generated according to the target database, and the application file identification features are identified by the application file identification engine, and whether the application file is a preset application file is determined according to the identification result.

[0089] This embodiment obtains static information of the application file; determines a single feature, multiple features and fuzzy features based on the static information; generates application file identification features based on the single feature, multiple features and fuzzy features; through the above method, after identifying the static information of the application file, determines a single feature, multiple features and fuzzy features based on the static information, and then generates multi-dimensional application file identification features based on the single feature, multiple features and fuzzy features, thereby improving the diversity of application file identification features, providing more features for subsequent identification of applications, and thereby reducing the false alarm rate and missed alarm rate of identification.

[0090] In one embodiment, if Figure 4 Based on the first embodiment, a second embodiment of the method for determining file identification features of the present invention is proposed. Step S10 includes:

[0091] Step S101, obtaining the download network address of the application file.

[0092] It should be understood that the download network address refers to the network address for downloading the application file, and the download network address can be a download link, for example, https: / / www.xx.com / downloadApp / download.html.

[0093] Further, step S101 includes: obtaining file download information from an application market, file download information from a web page, and file download information from a third-party channel; when there is download information of an application file in the file download information from the application market, or there is download information of an application file in the file download information from a web page, or there is download information of an application file in the file download information from a third-party channel, determining a download network address of the application file.

[0094] It can be understood that the file download information of the application market refers to the information of downloading program files using the application market, and the file download information includes the information of all applications that have been downloaded from the application market. Similarly, the file download information of the web page refers to the information of downloading application files using the web page. The third-party channel refers to other channels except the application market and the web page. After obtaining the download information of the application file, it is determined whether there is download information of the application file in the file download information of the application market, whether there is download information of the application file in the file download information of the web page, and whether there is download information of the application file in the file download information of the third-party channel. If any of the above conditions is met, the network address corresponding to the download information of the application file is used as the download network address of the application file.

[0095] Furthermore, the determining of the download network address of the application file includes: searching for file download information containing the download information of the application file to obtain the application file download information; and identifying the application file download information to obtain the download network address of the application file.

[0096] It should be understood that when determining that there is download information of an application file in the file download information of an application market, or there is download information of an application file in the file download information of a web page, or there is download information of an application file in the file download information of a third-party channel, the file download information in which the download information of the application file exists is searched, and then the searched application file download information is identified to obtain the network address corresponding to the download information in which the application file exists, and then the network address is used as the download network address of the application file.

[0097] Step S102, crawling the application file according to the download network address.

[0098] It is understandable that after the download network address is determined, the application file is crawled out according to the download network address.

[0099] Step S103: Identify the application file according to the static information identification strategy to obtain static information of the application file.

[0100] It should be understood that the static information identification strategy refers to a strategy for identifying static information. After the application files are crawled out, the static information identification strategy is used to identify the application files to obtain the static information of the application files.

[0101] Further, step S103 includes: performing resource analysis on the application file to obtain resource analysis results; performing decompilation analysis on the application file to obtain decompilation analysis results; identifying the resource analysis results and decompilation analysis results according to a static information identification strategy to obtain static information of the application file.

[0102] It is understandable that after crawling out the application files, it is necessary to perform resource analysis and decompilation analysis on the application files respectively to obtain resource analysis results and decompilation analysis results, and then use static information identification strategies to identify the resource analysis results and decompilation analysis results to obtain static information of the application files. The static information includes but is not limited to file size, package name, version number, certificate information, name, download network address, icon fuzzy hash, and file fuzzy hash, etc.

[0103] This embodiment obtains the download network address of the application file; crawls the application file according to the download network address; identifies the application file according to the static information identification strategy to obtain the static information of the application file; through the above method, after obtaining the download network address of the application file, the download network address is used to download the application file, and then the static information of the application file is identified according to the static information identification strategy, thereby effectively improving the accuracy and diversity of identifying static information.

[0104] In one embodiment, if Figure 5 Based on the first embodiment, a third embodiment of the method for determining file identification features of the present invention is proposed. Step S20 includes:

[0105] Step S201, extracting the static information.

[0106] It can be understood that after the static information of the application file is identified, the static information is extracted to obtain static information related to the identification feature.

[0107] Step S202, classifying the extracted static information to obtain multiple categories of static information.

[0108] It should be understood that the categories of the static information include attribute categories and fuzzy hash categories. After the extracted static information is obtained, the extracted static information is classified to obtain multi-category static information.

[0109] Step S203, determining a single feature, multiple features and fuzzy features according to the multi-category static information.

[0110] It can be understood that the multi-category static information includes attribute static information and fuzzy hash static information, and then single features and multiple features are identified based on the attribute static information, and fuzzy features are identified based on the fuzzy static information.

[0111] Furthermore, step S203 includes: obtaining attribute static information and fuzzy hash static information based on the multi-category static information; obtaining the icon MD5 of the application file; determining single static information based on the attribute static information and the icon MD5, and determining a single feature based on the single static information; combining several of the attribute static information, and determining multiple features based on the combined multi-attribute static information; determining a fuzzy feature based on the fuzzy hash static information.

[0112] It should be understood that the icon MD5 refers to the MD5 of the icon of the application file, and then the icon MD5 is added to the attribute static information to obtain a single static information, and then a single feature is identified based on the single static information. After obtaining the attribute static information, several attribute static information are combined. The combined attribute static information can be icon + package name, package name + download network address, and fuzzy features are identified based on the fuzzy hash static information, and the security attributes of the application file are judged based on the recognition results of the fuzzy features.

[0113] This embodiment extracts the static information; classifies the extracted static information to obtain multi-category static information; determines single features, multiple features and fuzzy features based on the multi-category static information; through the above method, after obtaining the static information, the static information is extracted, and then the extracted static information is divided into multi-category static information, and then the single feature, multiple features and fuzzy features are identified based on the multi-category static information, thereby effectively improving the diversity and accuracy of the recognition features.

[0114] In addition, an embodiment of the present invention further provides a storage medium, on which a file identification feature determination program is stored. When the file identification feature determination program is executed by a processor, the steps of the file identification feature determination method described above are implemented.

[0115] Since the storage medium adopts all the technical solutions of all the above embodiments, it has at least all the beneficial effects brought by the technical solutions of the above embodiments, which will not be described one by one here.

[0116] In addition, refer to Figure 6 The embodiment of the present invention further provides a device for determining a file identification feature, the device comprising:

[0117] The acquisition module 10 is used to acquire static information of the application program file.

[0118] The determination module 20 is used to determine a single feature, multiple features and fuzzy features according to the static information.

[0119] The generating module 30 is used to generate application file identification features according to the single feature, multiple features and fuzzy features.

[0120] This embodiment obtains static information of the application file; determines a single feature, multiple features and fuzzy features based on the static information; generates application file identification features based on the single feature, multiple features and fuzzy features; through the above method, after identifying the static information of the application file, determines a single feature, multiple features and fuzzy features based on the static information, and then generates multi-dimensional application file identification features based on the single feature, multiple features and fuzzy features, thereby improving the diversity of application file identification features, providing more features for subsequent identification of applications, and thereby reducing the false alarm rate and missed alarm rate of identification.

[0121] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of them according to actual needs to achieve the purpose of the present embodiment, and no limitation is made here.

[0122] In addition, for technical details not fully described in this embodiment, reference can be made to the file identification feature determination method provided in any embodiment of the present invention, and will not be repeated here.

[0123] In one embodiment, the acquisition module 10 is further used to obtain a download network address of the application file; crawl the application file according to the download network address; identify the application file according to a static information identification strategy to obtain static information of the application file.

[0124] In one embodiment, the acquisition module 10 is also used to obtain file download information from an application market, file download information from a web page, and file download information from a third-party channel; when there is download information of an application file in the file download information of the application market, or there is download information of an application file in the file download information of a web page, or there is download information of an application file in the file download information of a third-party channel, determine the download network address of the application file.

[0125] In one embodiment, the acquisition module 10 is further used to search for file download information containing the application file download information to obtain the application file download information; identify the application file download information to obtain the download network address of the application file.

[0126] In one embodiment, the acquisition module 10 is also used to perform resource analysis on the application file to obtain resource analysis results; perform decompilation analysis on the application file to obtain decompilation analysis results; identify the resource analysis results and decompilation analysis results according to the static information identification strategy to obtain static information of the application file.

[0127] In one embodiment, the determination module 20 is further used to extract the static information; classify the extracted static information to obtain multi-category static information; and determine single features, multiple features and fuzzy features based on the multi-category static information.

[0128] In one embodiment, the determination module 20 is also used to obtain attribute static information and fuzzy hash static information based on the multi-category static information; obtain the icon MD5 of the application file; determine a single static information based on the attribute static information and the icon MD5, and determine a single feature based on the single static information; combine several of the attribute static information, and determine multiple features based on the combined multi-attribute static information; determine the fuzzy feature based on the fuzzy hash static information.

[0129] In one embodiment, the generation module 30 is also used to obtain the importance of the single feature, multiple features and fuzzy features for identifying the application file; score the single feature, multiple features and fuzzy features according to the importance; mark the single feature, multiple features and fuzzy features according to the scoring scores; summarize the marked single feature and the scoring scores of the single feature, the marked multiple features and the scoring scores of the multiple features, the marked fuzzy features and the scoring scores of the fuzzy features to obtain a marked feature scoring data set; write the marked feature scoring data set to a target database for storing marked features and feature scoring scores, and generate application file identification features based on the target database.

[0130] In one embodiment, the generating module 30 is further configured to identify the application file identification feature through an application file identification engine; and determine whether the application file is a preset application file according to the identification result.

[0131] In one embodiment, the generating module 30 is further configured to mark the application file with a preset pseudo-label when the application file is determined to be a preset application file according to the recognition result; and classify the marked application file.

[0132] Other embodiments or implementation methods of the device for determining file identification features of the present invention may refer to the above-mentioned method embodiments, which will not be repeated here.

[0133] The present invention discloses A1, a method for determining a file identification feature, the method comprising the following steps:

[0134] Get static information of application files;

[0135] Determine a single feature, multiple features, and fuzzy features based on the static information;

[0136] An application file identification feature is generated according to the single feature, multiple features and fuzzy features.

[0137] A2. The method for determining file identification features as described in A1, wherein the step of obtaining static information of the application file comprises:

[0138] Get the download network address of the application file;

[0139] crawling the application file according to the download network address;

[0140] The application file is identified according to the static information identification strategy to obtain static information of the application file.

[0141] A3. The method for determining the file identification feature as described in A2, wherein the step of obtaining the download network address of the application file comprises:

[0142] Obtain file download information from application markets, web pages, and third-party channels;

[0143] When the file download information of the application market contains download information of the application file, the file download information of the web page contains download information of the application file, or the file download information of the third-party channel contains download information of the application file, the download network address of the application file is determined.

[0144] A4. The method for determining the file identification feature as described in A3, wherein determining the download network address of the application file comprises:

[0145] Searching for the file download information containing the download information of the application file to obtain the application file download information;

[0146] The application file download information is identified to obtain a download network address of the application file.

[0147] A5. The method for determining the file identification feature as described in A2, wherein the application file is identified according to the static information identification strategy to obtain the static information of the application file, including:

[0148] Performing resource analysis on the application file to obtain a resource analysis result;

[0149] Performing decompilation analysis on the application file to obtain a decompilation analysis result;

[0150] The resource analysis result and the decompilation analysis result are identified according to the static information identification strategy to obtain the static information of the application file.

[0151] A6. The method for determining file identification features as described in A1, wherein determining a single feature, multiple features, and fuzzy features based on the static information comprises:

[0152] Extracting the static information;

[0153] Classify the extracted static information to obtain multi-category static information;

[0154] Single features, multiple features and fuzzy features are determined according to the multi-category static information.

[0155] A7. The method for determining file recognition features as described in A6, wherein determining a single feature, multiple features, and fuzzy features based on the multi-category static information comprises:

[0156] Obtaining attribute static information and fuzzy hash static information according to the multi-category static information;

[0157] Get the icon MD5 of the application file;

[0158] Determine a single static information according to the attribute static information and the icon MD5, and determine a single feature according to the single static information;

[0159] Combining a plurality of the attribute static information, and determining multiple features according to the combined multiple attribute static information;

[0160] A fuzzy feature is determined according to the fuzzy hash static information.

[0161] A8. The method for determining a file identification feature as described in A1, wherein generating an application file identification feature based on the single feature, multiple features, and fuzzy features comprises:

[0162] Obtaining the importance of the single feature, multiple features, and fuzzy features for identifying the application file;

[0163] Scoring the single feature, multiple features and fuzzy features respectively according to the importance;

[0164] Marking the single feature, multiple features and fuzzy features respectively according to the scoring scores;

[0165] Summarize the single feature after labeling and the score of the single feature, the multiple features after labeling and the score of the multiple features, and the fuzzy features after labeling and the score of the fuzzy features to obtain a label feature score data set;

[0166] The marker feature scoring data set is written into a target database for storing marker features and feature scoring scores, and an application file identification feature is generated according to the target database.

[0167] A9. The method for determining a file identification feature according to claim 1, after generating the application file identification feature according to the single feature, multiple features and fuzzy features, further comprising:

[0168] Identify application file identification features through an application file identification engine;

[0169] It is determined whether the application file is a preset application file according to the recognition result.

[0170] A10. The method for determining a file identification feature as described in A9, after determining whether the application file is a preset application file according to the identification result, further comprising:

[0171] When the application file is determined to be a preset application file according to the recognition result, marking the application file by using a preset pseudo label;

[0172] Categorize the marked application files.

[0173] The present invention also discloses B11, a device for determining a file identification feature, the device comprising:

[0174] The acquisition module is used to obtain static information of application files;

[0175] A determination module, used to determine a single feature, multiple features and fuzzy features according to the static information;

[0176] A generation module is used to generate application file identification features based on the single feature, multiple features and fuzzy features.

[0177] B12. In the file identification feature determination device as described in B11, the acquisition module is also used to obtain a download network address of the application file; download the application file according to the download network address; identify the application file according to a static information identification strategy to obtain static information of the application file.

[0178] B13. In the file identification feature determination device as described in B12, the acquisition module is also used to obtain file download information from an application market, file download information from a web page, and file download information from a third-party channel; when there is download information of the application file in the file download information of the application market, or there is download information of the application file in the file download information of the web page, or there is download information of the application file in the file download information of the third-party channel, determine the download network address of the application file.

[0179] B14. In the file identification feature determination device as described in B12, the acquisition module is further used to perform resource analysis on the application file to obtain a resource analysis result; perform decompilation analysis on the application file to obtain a decompilation analysis result; and identify the resource analysis result and the decompilation analysis result according to a static information identification strategy to obtain static information of the application file.

[0180] B15. In the file recognition feature determination device as described in B11, the determination module is further used to extract the static information; classify the extracted static information to obtain multi-category static information; and determine single features, multiple features and fuzzy features based on the multi-category static information.

[0181] B16. The file identification feature determination device as described in claim 15, wherein the determination module is further used to obtain attribute feature information and fuzzy hash feature information based on the multi-category feature information; obtain the icon MD5 of the application file; determine a single feature based on the attribute feature information and the icon MD5; combine several of the attribute feature information and determine multiple features based on the combination result; and determine a fuzzy feature based on the fuzzy hash feature information.

[0182] B17. In the file identification feature determination device as described in B11, the generation module is further used to obtain the importance of the single feature, multiple features and fuzzy features for identifying the application file; score the single feature, multiple features and fuzzy features according to the importance; mark the single feature, multiple features and fuzzy features according to the scoring scores; summarize the marked single feature and the scoring scores of the single feature, the marked multiple features and the scoring scores of the multiple features, the marked fuzzy features and the scoring scores of the fuzzy features to obtain a marked feature scoring data set; write the marked feature scoring data set to a target database for storing marked features and feature scoring scores, and generate application file identification features according to the target database.

[0183] B18. In the file identification feature determination device as described in B11, the generation module is further used to identify the application file identification feature through an application file identification engine; and determine whether the application file is a preset application file based on the identification result.

[0184] In addition, it should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0185] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0186] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory (ROM) / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, an integrated platform workstation, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0187] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for determining a file identification feature, characterized in that: The method for determining the file identification feature comprises the following steps: Get static information of application files; Determine a single feature, multiple features, and fuzzy features based on the static information; An application file identification feature is generated according to the single feature, multiple features and fuzzy features.

2. The method for determining a file identification feature according to claim 1, wherein: The step of obtaining static information of the application file includes: Get the download network address of the application file; crawling the application file according to the download network address; The application file is identified according to the static information identification strategy to obtain static information of the application file.

3. The method for determining a file identification feature according to claim 2, wherein: The step of obtaining the download network address of the application file includes: Obtain file download information from application markets, web pages, and third-party channels; When the file download information of the application market contains download information of the application file, the file download information of the web page contains download information of the application file, or the file download information of the third-party channel contains download information of the application file, the download network address of the application file is determined.

4. The method for determining a file identification feature according to claim 3, wherein: Determining the download network address of the application file includes: Searching for the file download information containing the download information of the application file to obtain the application file download information; The application file download information is identified to obtain a download network address of the application file.

5. The method for determining a file identification feature according to claim 1, wherein: The determining of a single feature, multiple features and fuzzy features according to the static information includes: Extracting the static information; Classify the extracted static information to obtain multi-category static information; Single features, multiple features and fuzzy features are determined according to the multi-category static information.

6. The method for determining a file identification feature according to claim 5, wherein: The determining of a single feature, multiple features and fuzzy features according to the multi-category static information includes: Obtaining attribute static information and fuzzy hash static information according to the multi-category static information; Get the icon MD5 of the application file; Determine a single static information according to the attribute static information and the icon MD5, and determine a single feature according to the single static information; Combining a plurality of the attribute static information, and determining multiple features according to the combined multiple attribute static information; A fuzzy feature is determined according to the fuzzy hash static information.

7. The method for determining a file identification feature according to claim 1, wherein: The generating of the application file identification feature according to the single feature, multiple features and fuzzy features includes: Obtaining the importance of the single feature, multiple features, and fuzzy features for identifying the application file; Scoring the single feature, multiple features and fuzzy features respectively according to the importance; Marking the single feature, multiple features and fuzzy features respectively according to the scoring scores; Summarize the single feature after labeling and the score of the single feature, the multiple features after labeling and the score of the multiple features, and the fuzzy features after labeling and the score of the fuzzy features to obtain a label feature score data set; The marker feature scoring data set is written into a target database for storing marker features and feature scoring scores, and an application file identification feature is generated according to the target database.

8. A device for determining a file identification feature, characterized in that: The file identification feature determination device comprises: The acquisition module is used to obtain static information of application files; A determination module, used to determine a single feature, multiple features and fuzzy features according to the static information; A generation module is used to generate application file identification features based on the single feature, multiple features and fuzzy features.

9. A device for determining a file identification feature, characterized in that: The file identification feature determination device comprises: a memory, a processor, and a file identification feature determination program stored in the memory and executable on the processor, wherein the file identification feature determination program is configured to implement the file identification feature determination method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores a file identification feature determination program, which, when executed by a processor, implements the file identification feature determination method according to any one of claims 1 to 7.