WO2016197710A1 - 移动终端软件假界面识别方法及装置 - Google Patents

移动终端软件假界面识别方法及装置 Download PDF

Info

Publication number
WO2016197710A1
WO2016197710A1 PCT/CN2016/079922 CN2016079922W WO2016197710A1 WO 2016197710 A1 WO2016197710 A1 WO 2016197710A1 CN 2016079922 W CN2016079922 W CN 2016079922W WO 2016197710 A1 WO2016197710 A1 WO 2016197710A1
Authority
WO
WIPO (PCT)
Prior art keywords
feature
screenshot
information
matching
software
Prior art date
Application number
PCT/CN2016/079922
Other languages
English (en)
French (fr)
Inventor
张冬明
Original Assignee
中兴通讯股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 中兴通讯股份有限公司 filed Critical 中兴通讯股份有限公司
Publication of WO2016197710A1 publication Critical patent/WO2016197710A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/50Monitoring users, programs or devices to maintain the integrity of platforms, e.g. of processors, firmware or operating systems
    • G06F21/55Detecting local intrusion or implementing counter-measures
    • G06F21/56Computer malware detection or handling, e.g. anti-virus arrangements
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/583Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/50Monitoring users, programs or devices to maintain the integrity of platforms, e.g. of processors, firmware or operating systems
    • G06F21/57Certifying or maintaining trusted computer platforms, e.g. secure boots or power-downs, version controls, system software checks, secure updates or assessing vulnerabilities

Definitions

  • This document relates to, but is not limited to, to the field of mobile communications, and in particular to a mobile terminal software fake interface identification method and apparatus.
  • the mobile phone plays an increasingly important role in the user's life. Users will install a variety of software in the mobile phone. When using the mobile phone software, they often encounter the phishing software of the camouflage interface. The interface of these phishing software is done. The interface with the original software is very realistic, and it is very easy for users to believe in it and be defrauded or reveal personal privacy. Today, with the rapid development of smart phones and mobile Internet, there are many cases of similar phishing scams disclosed in various media, and it is of great significance to identify the phishing interface technically.
  • the anti-phishing technology mainly compares the security of the URL address information of the phishing website, and whether there is a Trojan to judge. That is to say, the anti-phishing in the related art mainly solves the problems of whether there is a Trojan, whether there is a virus, and whether the website is safe in the website, but the anti-phishing identification of the interface of the mobile phone software is not involved. Therefore, there is an urgent need for a technical solution for identifying a fake interface and alerting the user to solve the fraud problem of the camouflage software in the smart phone.
  • the embodiment of the invention provides a method and a device for identifying a fake interface of a mobile terminal software, which can alleviate the situation of disguising software fraud on the terminal.
  • a method for identifying a fake interface of a mobile terminal software comprising:
  • the image feature library includes: image feature information of the software user interface UI; and if the matching is successful, the software of the UI screenshot is
  • the additional information is feature-matched with the additional feature library, the additional feature library comprising: software additional information in addition to the image feature information; if the matching is unsuccessful, determining that the UI screenshot is a fake interface suspected of camouflage.
  • the method further includes: establishing the image feature library and an additional feature library.
  • the method further includes:
  • image feature information of the UI screenshot fails to match the image feature database
  • image feature information of the UI screenshot is added to the image feature library according to a user's selection, and the UI screenshot is Software additional information is added to the additional feature library.
  • the UI screenshot of the obtaining software includes:
  • the relevant interface is automatically screenshotd to obtain the screenshot of the UI; or,
  • a screenshot is taken on the application interface currently displayed by the user, and the UI screenshot is obtained.
  • the image feature library includes: a trust image feature library, and a camouflage image feature library;
  • the additional feature library includes: a trust additional feature library, and a camouflage additional feature library;
  • the matching the image feature information of the UI screenshot with the image feature library includes:
  • the matching the software additional information of the UI screenshot with the additional feature library includes:
  • the software additional information of the UI screenshot is matched with the masqueted additional feature library, and if the matching fails, the software additional information of the UI screenshot is continuously matched with the trusted additional feature library.
  • the image feature information in the image feature library is: a multi-level feature vector set including a statistical feature and an original pixel feature, where the statistical feature includes: a numerical statistical value obtained by calculating a predetermined feature of the image,
  • the original pixel feature includes: original image pixel data or normalized pixel data subjected to image size adjustment and sampling processing;
  • the software additional information in the additional feature library is: a multi-level feature vector set including simple information and original data features, wherein the simple information includes: software basic information, and the original data features include: software depth information;
  • the matching the image feature information of the UI screenshot with the image feature library includes:
  • the original pixel feature in the image feature information of the UI screenshot is correlated with the original pixel feature in the image feature library, and if the original pixel is If the matching degree of the feature is greater than or equal to the second predetermined threshold, confirming that the feature matching is successful, and confirming that the feature matching fails if the matching degree of the original pixel feature is less than the second predetermined threshold;
  • the matching the software additional information of the UI screenshot with the additional feature library includes:
  • the method further includes:
  • a mobile terminal software fake interface identification device comprising:
  • An extraction module configured to acquire a UI screenshot of the software, extract image feature information of the UI screenshot, and software additional information on the UI screenshot;
  • a matching module configured to match image feature information of the UI screenshot with the image feature library, where the image feature library includes: image feature information of the software user interface UI; in the case of successful matching, The software additional information of the UI screenshot is matched with the additional feature library, the additional feature library includes: software additional information other than the image feature information; if the matching is unsuccessful, the UI screenshot is determined to be a suspected camouflage Fake interface.
  • the apparatus further includes: an establishing module configured to establish an image feature library and an additional feature library.
  • the device further includes:
  • Adding a module configured to add image feature information of the UI screenshot to the image feature library according to a user's selection if the image feature information of the UI screenshot fails to match the image feature database, and The software additional information of the UI screenshot is added to the additional feature library, and the operation is ended if the user does not add.
  • the UI screenshot of the extraction module acquiring software includes:
  • the extracting module automatically takes a screenshot of the related interface when the software is started, when the interface is switched during the running of the software, or when the interface containing the sensitive control element is opened, and the UI screenshot is obtained; or
  • the extraction module performs a screenshot on the application interface currently displayed by the user according to the user's call, and acquires the UI screenshot.
  • the image feature library includes: a trust image feature library, and a camouflage image feature library;
  • the additional feature library includes: a trust additional feature library, and a camouflage additional feature library;
  • the matching module matching the image feature information of the UI screenshot with the image feature library includes:
  • the matching module performs feature matching on the image feature information of the UI screenshot and the camouflage image feature library, and if the matching fails, the image feature information of the UI screenshot is continuously matched with the trusted image feature library;
  • the matching module performs software extension information of the UI screenshot with the additional feature library
  • the match matches include:
  • the matching module matches the software additional information of the UI screenshot with the masqueted additional feature library. If the matching fails, the software additional information of the UI screenshot is continuously matched with the trusted additional feature database.
  • the image feature information in the image feature library is: a multi-level feature vector set including a statistical feature and an original pixel feature, where the statistical feature includes: a numerical statistical value obtained by calculating a predetermined feature of the image,
  • the original pixel features include original image pixel data or normalized pixel data subjected to image resizing and sampling processing;
  • the software additional information in the additional feature library is: a multi-level feature vector set including simple information and original data features, the simple information includes: software basic information, and the original data features include: software depth information;
  • the matching module matching the image feature information of the UI screenshot with the image feature library includes:
  • the original pixel feature in the image feature information of the UI screenshot is correlated with the original pixel feature in the image feature library, and if the original pixel is If the matching degree of the feature is greater than or equal to the second predetermined threshold, confirming that the feature matching is successful, and confirming that the feature matching fails if the matching degree of the original pixel feature is less than the second predetermined threshold;
  • the device further includes:
  • an update module configured to acquire image feature information and software additional information of the UI fed back by the user, and update the image feature library and the additional feature library.
  • a computer readable storage medium storing computer executable instructions for performing the above method.
  • the problem of camouflage software fraud on the smart phone in the related art can be alleviated, and the problem can be quickly
  • the phishing software recognizes and improves the security of the terminal.
  • FIG. 1 is a flowchart of a method for identifying a fake interface of a mobile terminal software according to an embodiment of the present invention
  • FIG. 2 is a flowchart of an alternative manner of a fake interface identification method for a mobile terminal software according to an embodiment of the present invention
  • FIG. 3 is a flowchart of an example of a method for identifying a fake interface of a mobile terminal software according to an embodiment of the present invention
  • FIG. 4 is a schematic structural diagram of a mobile terminal software fake interface identification apparatus according to an embodiment of the present invention.
  • FIG. 5 is a schematic structural diagram of an alternative embodiment of a mobile terminal software fake interface identification apparatus according to an embodiment of the present invention.
  • an embodiment of the present invention provides a method and device for identifying a fake interface of a mobile terminal software.
  • FIG. 1 is a flowchart of a mobile terminal software fake interface identification method according to an embodiment of the present invention. As shown in FIG. 1, the mobile terminal software according to an embodiment of the present invention is shown.
  • the fake interface identification method includes the following steps 102-103:
  • Step 102 Obtain a UI screenshot of the software, extract image feature information of the UI screenshot, and software additional information on the UI screenshot;
  • Step 103 Match image feature information of the UI screenshot with the image feature library, where the image feature library includes: image feature information of the software user interface UI; and if the matching is successful, the software additional information of the UI screenshot is The additional feature library performs feature matching, and the additional feature library includes: software additional information in addition to the image feature information; if the matching is unsuccessful, the UI screenshot is determined to be a fake interface suspected of camouflage.
  • the software additional information of the UI screenshot is successfully matched with the additional feature library, it may be determined that the UI screenshot is a regular interface.
  • FIG. 2 An alternative of this embodiment is shown in FIG. 2, and may further include: before step 102:
  • step 101 an image feature library and an additional feature library are created.
  • the image feature information in the image feature library is: a multi-level feature vector set including a statistical feature and an original pixel feature, where the statistical feature includes: a numerical value obtained by calculating a predetermined feature of the image, and the original pixel Features include raw image pixel data or normalized pixel data subjected to image resizing and sampling processing;
  • the software additional information in the additional feature library is: a multi-level feature vector set including simple information and original data features, the simple information includes: software basic information, and the original data features include: software depth information.
  • the image feature library includes: a trust image feature library, and a camouflage image feature library;
  • the additional feature library includes: a trust additional feature library, and a camouflage additional feature library.
  • the image features of the trust software are stored in the trust image feature library.
  • the image features of the camouflage software are stored in the camouflage image feature library.
  • the additional feature library is stored to store additional features of the trust software.
  • the camouflage additional feature library stores additional features of the camouflage software.
  • the foregoing software may be any software, in order to To protect the privacy of users, the above software can also be used for high-risk smartphone software such as user privacy or wealth management.
  • the UI screenshot of the obtaining software includes:
  • the relevant interface is automatically screenshotd to obtain a screenshot of the UI; or, according to the user's call, the application currently displayed by the user is displayed. Take a screenshot of the interface and get a screenshot of the UI.
  • step 103 After performing step 103, if it is determined that the UI screenshot is a fake interface suspected of masquerading, the user may also be prompted for pirated software.
  • the method further includes:
  • the image feature information of the UI screenshot fails to match the image feature database, according to the user's selection, the image feature information of the UI screenshot is added to the image feature library, and the software additional information of the UI screenshot is added to the additional feature library, if The user can end the operation without adding it.
  • performing feature matching on the image feature information of the UI screenshot and the image feature library includes: matching the image feature information of the UI screenshot with the camouflage image feature library, and if the matching fails, the UI screenshot is The image feature information and the trusted image feature library continue to perform feature matching;
  • matching the software additional information of the UI screenshot with the additional feature library includes: matching the software additional information of the UI screenshot with the camouflage additional feature library, and if the matching fails, the software additional information of the UI screenshot is Trust the additional signature library to continue feature matching.
  • the matching the image feature information of the UI screenshot with the image feature library includes:
  • the original pixel feature in the image feature information of the UI screenshot is correlated with the original pixel feature in the image feature library, and the matching is performed, if the matching degree of the original pixel feature If the second predetermined threshold is greater than or equal to the second predetermined threshold, it is confirmed that the feature matching is successful, and if the matching degree of the original pixel feature is less than the second predetermined threshold, the feature matching failure is confirmed;
  • the feature matching of the software additional information of the UI screenshot with the additional feature library includes:
  • the method may further include: acquiring image feature information and software additional information of the software user interface UI fed back by the user, and updating the image feature library and the additional feature library, thereby continuously improving the image feature library and the additional feature library. ; can be, but is not limited to, obtaining user feedback via the Internet.
  • an image feature library and an additional feature library including other information than image features are established in advance for commonly used high-risk smartphone software involving user privacy or wealth management.
  • the interface is switched during the running process, or the interface containing the sensitive control element is opened, the related interface is screenshotd, and the image feature information is extracted from the screenshot.
  • the image feature library and the additional feature library may pre-establish partial samples.
  • the image feature library and the additional feature library may be further refined and expanded according to the user's operation and judgment during the user's use.
  • a multi-level feature vector set may be established when extracting image features and additional features, and some preliminary statistical values or direct simple features are used for fast comparison rough selection in feature extraction, and For some original sampling data features, the original data in the feature database is correlated with the relevant data of the application software to perform deep feature matching.
  • This multi-level feature vector feature matching method can significantly improve the computational efficiency of anti-phishing interface recognition.
  • FIG. 3 is a flowchart of an example of a method for identifying a fake interface of a mobile terminal software according to an embodiment of the present invention. As shown in FIG. 3, the following steps 1 to 4 are included:
  • a UI image image feature library containing a certain number of samples and an additional feature library other than the image information are established in advance for commonly used high-risk smartphone software involving user privacy or wealth management.
  • the image feature library contains information that distinguishes common image feature information of the image, including but not limited to normalized image brightness, color, texture, edges, focus, lines, histograms, grayscale images, and the like.
  • the additional feature library included in the image information includes, but is not limited to, software name, version information, signature information, file bytecode sampling features, and the like.
  • a typical implementation is to create a multi-level feature vector set containing statistical features and original pixel features.
  • Statistical features refer to the calculation of certain features of an image to obtain direct, simple numerical statistical values, such as the distribution ratio of multiple color components in multiple interval segments, the specific local spatial position of the image, or the mean of the global pixel grayscale values. , variance, etc.; the original pixel feature refers to the specific normalization, sampling and other simple processing of the image and directly store the relevant pixel data.
  • the statistical features are used to quickly compare coarse-step screening with the application software screenshots during subsequent feature comparisons, and the original pixel features are used for subsequent computational depth matching with the application software screenshots for subsequent feature comparisons.
  • a typical implementation may employ a manner similar to the above image feature library to create a multi-level feature vector set containing simple information and original data features.
  • the simple information includes rough information such as software name, version information, and file size, and the original data features include data of the signature file and the bytecode sampling information.
  • Simple information is used for application software for quick comparison, and raw data features are used to perform relevant computational depth matching with the application software.
  • Step 2 When the monitoring application software interface is opened and run, the UI interface of the software is screenshotd, and the image feature information of the screenshot and other additional information of the interface itself are extracted.
  • the image feature information and the parameter types extracted by the additional information refer completely to the related feature information described in step 1. Since the mobile application usually contains multiple interfaces, the interface can also be re-screened after the interface is switched, and the new image feature matching is started according to step 3.
  • the software interface control properties can be automatically detected, and only the interface containing the password input box, payment characters and other sensitive attributes can be used to initiate screenshot and image feature matching.
  • Step 3 performing image feature matching on the image feature information of the screenshot and the image feature information of the image feature library. If the matching is successful, the interface itself may be a formal software, or may be a fake interface, and step 4 is performed; if the matching is unsuccessful, The image feature library itself does not include the image feature information matched by the interface. At this time, if the user selects to manually add the feature library, the image feature information extracted by the interface is added into the image feature library, and the software of the software may be attached. The information is added to the additional information library to further improve the library information. If the user does not add, the monitoring is ended.
  • the typical implementation method is based on the multi-level feature vector set of step 1.
  • the simple information such as statistical features is quickly matched for primary selection, and under the premise that the primary selection satisfies the matching similarity,
  • the original pixel features of the software screenshot are correlated with the original pixel features of each sample of the image feature library, and the similarity is accurately calculated.
  • the statistical feature is only a calculation of the image itself to obtain a numerical statistical result.
  • the data in the image feature library is compared with the screenshot of the application software, which is only a direct numerical comparison, and the original pixel feature needs to be screenshotd with the application software when matching.
  • Related features are correlated, such as direct pixel difference, variance, correlation coefficient, PSNR, quality factor, and so on.
  • Step 4 matching the software additional information related to the interface with the additional information base. If the matching is successful, the interface is a normal interface, and the monitoring is ended; if the matching is unsuccessful, the interface is a fake interface suspected of disguising, and the user is camouflaged. A fake interface/fishing interface reminder. For the scene of the re-screening of the interface that may involve the switching of the interface during the running of the same software, if the additional information identification has been performed before, the judgment conclusion is directly obtained according to the previous authentication result, and no re-recognition is needed.
  • the typical implementation method is based on the multi-level feature vector set of step 1.
  • the simple information is quickly matched for primary selection, and the original of the software is satisfied on the premise that the primary selection satisfies the matching similarity.
  • the data features are correlated with the original data features of each sample of the feature library, and the similarity is accurately calculated.
  • the image feature library and the additional information library can be continuously updated and improved through a networked manner and a large number of user feedback operations.
  • the image feature library and the additional feature library itself can be further divided into a trust feature library and a masquerading (malicious) feature library.
  • the malicious feature library can improve the prioritization of the priority database to speed up the matching speed.
  • the embodiment of the present invention automatically takes a screenshot after monitoring the startup of the mobile application software.
  • specific UI presentation mode such as floating window button, mobile phone system control, system specific button response, voice command, etc., allows the user to display the anti-spoofing identification of the application interface without enabling automatic Feature identification function, which makes detection more efficient, and there is no problem of redundant screenshots for multi-interface switching applications.
  • the embodiment of the present invention takes the image feature of the interface screenshot as the main recognition basis, and further determines whether the interface is a suspected fake interface by combining other additional information outside the interface.
  • the technical solution of the embodiment of the present invention at least partially solves the phishing interface that often occurs at present, and illegally acquires problems such as a bank card password and personal identity privacy data.
  • the security software based on the embodiment of the invention has important practical value and broad application prospect.
  • the embodiment of the invention further provides a computer readable storage medium storing computer executable instructions for performing the above method.
  • FIG. 4 is a schematic structural diagram of a mobile terminal software fake interface identification device according to an embodiment of the present invention. As shown in FIG. 4, according to an embodiment of the present invention, The mobile terminal software fake interface identification device includes an extraction module 32 and a matching module 34.
  • the extraction module 32 is configured to acquire a UI screenshot of the software, extract image feature information of the UI screenshot, and software additional information on the UI screenshot;
  • the matching module 34 is configured to match the image feature information of the UI screenshot with the image feature library, where the image feature library includes: image feature information of the software user interface UI; if the matching is successful, the software of the UI screenshot is attached.
  • the information is feature-matched with the additional feature library, the additional feature library includes: software additional information in addition to the image feature information; if the matching is unsuccessful, the UI screenshot is determined to be a fake interface suspected of camouflage.
  • the software additional information of the UI screenshot is successfully matched with the additional feature library, it may be determined that the UI screenshot is a regular interface.
  • FIG. 5 An alternative of this embodiment is shown in FIG. 5, and the apparatus may further include:
  • the building module 30 is configured to create an image feature library and an additional feature library.
  • the image feature library includes: a trusted image feature library, and a camouflage image feature library; Additional feature libraries include: trust additional feature libraries, and masquerading additional feature libraries.
  • the image feature information in the image feature library is: a multi-level feature vector set including a statistical feature and an original pixel feature, wherein the statistical feature includes: a numerical statistical value obtained by calculating a predetermined feature of the image,
  • the original pixel features include original image pixel data or normalized pixel data subjected to image resizing and sampling processing;
  • the software additional information in the additional feature library is: a multi-level feature vector set including simple information and original data features,
  • the simple information includes: basic information of the software, and the original data features include: software depth information.
  • the UI module of the extraction module 32 acquiring the software includes:
  • the extracting module 32 automatically takes a screenshot of the related interface when the software is started, when the interface is switched during the running of the software, or when the interface containing the sensitive control element is opened, and the UI screenshot is obtained; or the extraction module is based on the user.
  • the call take a screenshot of the application interface currently displayed by the user, and obtain a screenshot of the UI.
  • the matching module 34 may be further configured to prompt the user to pirate software after determining that the UI screenshot is a fake interface suspected of masquerading.
  • the matching module 34 performs feature matching on the image feature information of the UI screenshot with the image feature library, including:
  • the matching module 34 performs feature matching on the image feature information of the UI screenshot and the camouflage image feature library. If the matching fails, the image feature information of the UI screenshot and the trusted image feature library are continuously matched with the feature;
  • the matching module 34 performs feature matching on the software additional information of the UI screenshot with the additional feature library, including:
  • the software additional information of the UI screenshot is matched with the camouflage additional feature library. If the matching fails, the software additional information of the UI screenshot is matched with the trust additional feature library to continue the feature matching.
  • the matching module 34 performs feature matching on the image feature information of the UI screenshot with the image feature library, including:
  • the matching module 34 matches the statistical feature in the image feature information of the UI screenshot with the statistical feature in the image feature database, and confirms that the feature matching fails in the case that the matching degree of the statistical feature is less than the first predetermined threshold.
  • the matching degree is greater than or equal to the first predetermined threshold
  • the matching module 34 performs feature matching on the software additional information of the UI screenshot with the additional feature library, including:
  • the matching module 34 matches the simple information in the software additional information of the UI screenshot with the simple information in the additional feature database, and confirms that the feature matching fails in the case where the matching degree of the simple information is less than the third predetermined threshold. If the matching degree is greater than or equal to the third predetermined threshold, matching the original data features in the software additional information of the UI screenshot with the original data features in the additional feature database for correlation calculation, and matching, if original If the matching degree of the data feature is greater than or equal to the fourth predetermined threshold, it is confirmed that the feature matching is successful, and if the matching degree of the original data feature is less than the fourth predetermined threshold, the feature matching failure is confirmed.
  • the foregoing apparatus may further include:
  • the image feature information of the UI screenshot fails to match the image feature database, according to the user's selection, the image feature information of the UI screenshot is added to the image feature library, and the software additional information of the UI screenshot is added to Additional feature library, if the user does not add, you can end the operation.
  • the foregoing apparatus may further include:
  • the update module is configured to obtain image feature information and software additional information of the software user interface UI fed back by the user, and update the image feature library and the additional feature library, thereby continuously improving the image feature library and the additional feature library; the update module may But not limited to getting user feedback via the Internet.
  • the technical solution of the embodiment of the present invention compares the image feature library and the additional feature library including other information except the image feature with the screenshot of the software-related interface to determine whether it is a suspected fake interface, and alleviates the camouflage on the smart phone in the prior art.
  • the problem of software fraud can quickly identify the phishing software and improve the security of the user's mobile phone.
  • modules in the client in the embodiment can be adaptively changed and placed in one or more clients different from the embodiment.
  • the modules in the embodiments can be combined into one module, and further they can be divided into a plurality of sub-modules or sub-units or sub-components.
  • any combination of the features disclosed in the specification, including the accompanying claims, the abstract and the drawings, and any methods so disclosed, or All processes or units of the client are combined.
  • Each feature disclosed in this specification may be replaced by alternative features that provide the same, equivalent or similar purpose.
  • Each of the component embodiments of the present invention may be implemented in hardware, or in a software module running on one or more processors, or in a combination thereof.
  • a microprocessor or digital signal processor may be used in practice to implement some or all of the functionality of some or all of the components loaded with the ordered web address in accordance with an embodiment of the present invention.
  • Embodiments of the invention may also be implemented as a device or device program (e.g., a computer program and a computer program product) for performing some or all of the methods described herein.
  • Such a program implementing an embodiment of the invention may be stored on a computer readable medium or may be in the form of one or more signals. Such signals may be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.
  • the embodiment of the present invention compares the image feature library and the additional feature library including other information except the image feature with the screenshot of the software-related interface to determine whether it is a suspected fake interface, and can alleviate the problem of camouflage software fraud on the smart phone in the related art. It can quickly identify the phishing software and improve the security of the terminal.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Security & Cryptography (AREA)
  • Theoretical Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Computer Hardware Design (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Virology (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Library & Information Science (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Telephone Function (AREA)
  • Stored Programmes (AREA)

Abstract

一种移动终端软件假界面识别方法及装置。该方法包括:获取软件的UI截图,提取UI截图的图像特征信息以及UI截图上的软件附加信息;将UI截图的图像特征信息与图像特征库进行特征匹配,图像特征库中包括:软件用户界面UI的图像特征信息;在匹配成功的情况下,将UI截图的软件附加信息与附加特征库进行特征匹配,附加特征库包括:除图像特征信息之外的软件附加信息;如果匹配不成功则确定UI截图为疑似伪装的假界面。

Description

移动终端软件假界面识别方法及装置 技术领域
本文涉及但不限于涉及移动通讯领域,特别是涉及一种移动终端软件假界面识别方法及装置。
背景技术
手机在用户的生活中扮演者越来越重要的角色,用户会在手机中安装各种各样的软件,在使用手机软件时,经常会遇到伪装界面的钓鱼软件,这些钓鱼软件的界面做的和原版软件界面非常逼真,非常容易让用户信以为真,从而被诈骗钱财或泄露个人隐私。在智能手机和移动互联网飞速发展的今天,各类媒体上披露的类似的被钓鱼诈骗的案例非常多,从技术上对钓鱼界面进行识别具有重要意义。
在相关技术中,防钓鱼技术主要针对钓鱼网站的URL地址信息的安全性进行比对,以及是否有木马进行判断。也就是说,相关技术中的防钓鱼主要是解决网站中是否有木马、是否有病毒,网址是否安全等问题,但对手机软件运行时的界面进行防钓鱼鉴别并未涉及。因此,目前急需一种对假界面进行鉴别,并对用户进行预警提醒,从而解决智能手机中伪装软件的欺诈问题的技术方案。
发明内容
以下是对本文详细描述的主题的概述。本概述并非是为了限制权利要求的保护范围。
本发明实施例提供一种移动终端软件假界面识别方法及装置,可以缓解终端上伪装软件欺诈的情况。
本发明实施例采用如下技术方案。
一种移动终端软件假界面识别方法,包括:
获取软件的UI截图,提取所述UI截图的图像特征信息以及所述UI截图 上的软件附加信息;
将所述UI截图的图像特征信息与所述图像特征库进行特征匹配,所述图像特征库中包括:软件用户界面UI的图像特征信息;在匹配成功的情况下,将所述UI截图的软件附加信息与所述附加特征库进行特征匹配,所述附加特征库包括:除所述图像特征信息之外的软件附加信息;如果匹配不成功则确定所述UI截图为疑似伪装的假界面。
可选地,所述获取软件的UI截图前还包括:建立所述图像特征库和附加特征库。
可选地,所述的方法还包括:
在所述UI截图的图像特征信息与所述图像特征库匹配失败的情况下,根据用户的选择,将所述UI截图的图像特征信息添加到所述图像特征库,并将所述UI截图的软件附加信息添加到所述附加特征库。
可选地,所述获取软件的UI截图包括:
在软件被启动运行时、软件运行过程中界面切换时、或包含敏感控件元素的界面被打开时,自动对相关界面进行截图,获取所述UI截图;或者,
根据用户的调用,对用户当前显示的应用界面进行截图,获取所述UI截图。
可选地,所述图像特征库包括:信任图像特征库、以及伪装图像特征库;所述附加特征库包括:信任附加特征库、以及伪装附加特征库;
所述将UI截图的图像特征信息与所述图像特征库进行特征匹配包括:
将所述UI截图的图像特征信息与所述伪装图像特征库进行特征匹配,如果匹配失败,则将所述UI截图的图像特征信息与所述信任图像特征库继续进行特征匹配;
所述将UI截图的软件附加信息与所述附加特征库进行特征匹配包括:
将所述UI截图的软件附加信息与所述伪装附加特征库进行特征匹配,如果匹配失败,则将所述UI截图的软件附加信息与所述信任附加特征库继续进行特征匹配。
可选地,所述图像特征库中的图像特征信息为:包括统计特征和原始像素特征的多层次特征向量集,所述统计特征包括:对图像的预定特征进行计算所得到的数值统计值,所述原始像素特征包括:原始图像像素数据或经过图像大小调整和抽样处理的归一化像素数据;
所述附加特征库中的软件附加信息为:包括简单信息、和原始数据特征的多层次特征向量集,其中,所述简单信息包括:软件基本信息,所述原始数据特征包括:软件深度信息;
所述将UI截图的图像特征信息与所述图像特征库进行特征匹配包括:
将所述UI截图的图像特征信息中的统计特征与所述图像特征库中的统计特征进行匹配,在统计特征的匹配度小于第一预定阈值的情况下,确认特征匹配失败,在统计特征的匹配度大于或等于第一预定阈值的情况下,对所述UI截图的图像特征信息中的原始像素特征与所述所述图像特征库中的原始像素特征进行相关计算、和匹配,如果原始像素特征的匹配度大于或等于第二预定阈值,则确认特征匹配成功,如果原始像素特征的匹配度小于第二预定阈值则确认特征匹配失败;
所述将UI截图的软件附加信息与所述附加特征库进行特征匹配包括:
将所述UI截图的软件附加信息中的简单信息与所述附加特征库中的简单信息进行匹配,在简单信息的匹配度小于第三预定阈值的情况下,确认特征匹配失败,在简单信息的匹配度大于或等于第三预定阈值的情况下,将所述UI截图的软件附加信息中的原始数据特征与所述附加特征库中的原始数据特征进行匹配进行相关计算、和匹配,如果原始数据特征的匹配度大于或等于第四预定阈值,则确认特征匹配成功,如果原始数据特征的匹配度小于第四预定阈值则确认特征匹配失败。
可选地,所述的方法还包括:
获取用户反馈的UI的图像特征信息和软件附加信息,并对所述图像特征库和所述附加特征库进行更新。
一种移动终端软件假界面识别装置,包括:
提取模块,设置成获取软件的UI截图,提取所述UI截图的图像特征信息以及所述UI截图上的软件附加信息;
匹配模块,设置成将所述UI截图的图像特征信息与所述图像特征库进行特征匹配,所述图像特征库中包括:软件用户界面UI的图像特征信息;在匹配成功的情况下,将所述UI截图的软件附加信息与所述附加特征库进行特征匹配,所述附加特征库包括:除所述图像特征信息之外的软件附加信息;如果匹配不成功则确定所述UI截图为疑似伪装的假界面。
可选地,所述的装置还包括:建立模块,设置成建立图像特征库和附加特征库。
可选地,所述的装置还包括:
添加模块,设置成在所述UI截图的图像特征信息与所述图像特征库匹配失败的情况下,根据用户的选择,将所述UI截图的图像特征信息添加到所述图像特征库,并将所述UI截图的软件附加信息添加到所述附加特征库,如果用户不添加则结束操作。
可选地,所述提取模块获取软件的UI截图包括:
所述提取模块在软件被启动运行时、软件运行过程中界面切换时、或包含敏感控件元素的界面被打开时,自动对相关界面进行截图,获取所述UI截图;或者,
所述提取模块根据用户的调用,对用户当前显示的应用界面进行截图,获取所述UI截图。
可选地,所述图像特征库包括:信任图像特征库、以及伪装图像特征库;所述附加特征库包括:信任附加特征库、以及伪装附加特征库;
所述匹配模块将UI截图的图像特征信息与所述图像特征库进行特征匹配包括:
所述匹配模块将所述UI截图的图像特征信息与所述伪装图像特征库进行特征匹配,如果匹配失败,则将所述UI截图的图像特征信息与所述信任图像特征库继续进行特征匹配;
所述匹配模块将所述UI截图的软件附加信息与所述附加特征库进行特 征匹配包括:
所述匹配模块将所述UI截图的软件附加信息与所述伪装附加特征库进行特征匹配,如果匹配失败,则将所述UI截图的软件附加信息与所述信任附加特征库继续进行特征匹配。
可选地,所述图像特征库中的图像特征信息为:包括统计特征和原始像素特征的多层次特征向量集,所述统计特征包括:对图像的预定特征进行计算所得到的数值统计值,所述原始像素特征包括原始图像像素数据或经过图像大小调整和抽样处理的归一化像素数据;
所述附加特征库中的软件附加信息为:包括简单信息、和原始数据特征的多层次特征向量集,所述简单信息包括:软件基本信息,所述原始数据特征包括:软件深度信息;
所述匹配模块将UI截图的图像特征信息与所述图像特征库进行特征匹配包括:
将所述UI截图的图像特征信息中的统计特征与所述图像特征库中的统计特征进行匹配,在统计特征的匹配度小于第一预定阈值的情况下,确认特征匹配失败,在统计特征的匹配度大于或等于第一预定阈值的情况下,对所述UI截图的图像特征信息中的原始像素特征与所述所述图像特征库中的原始像素特征进行相关计算、和匹配,如果原始像素特征的匹配度大于或等于第二预定阈值,则确认特征匹配成功,如果原始像素特征的匹配度小于第二预定阈值则确认特征匹配失败;
将所述UI截图的软件附加信息中的简单信息与所述附加特征库中的简单信息进行匹配,在简单信息的匹配度小于第三预定阈值的情况下,确认特征匹配失败,在简单信息的匹配度大于或等于第三预定阈值的情况下,将所述UI截图的软件附加信息中的原始数据特征与所述附加特征库中的原始数据特征进行匹配进行相关计算、和匹配,如果原始数据特征的匹配度大于或等于第四预定阈值,则确认特征匹配成功,如果原始数据特征的匹配度小于第四预定阈值则确认特征匹配失败。
可选地,所述的装置还包括:
更新模块,设置成获取用户反馈的UI的图像特征信息和软件附加信息,并对所述图像特征库和所述附加特征库进行更新。
一种计算机可读存储介质,存储有计算机可执行指令,所述计算机可执行指令用于执行上述方法。
本发明实施例的有益效果如下:
通过建立图像特征库以及包含图像特征外其他信息的附加特征库与软件相关界面的截图进行对比来判断是否为疑似假界面,可以缓解相关技术中智能手机上伪装软件欺诈的问题,能够快速的对钓鱼软件进行识别,提高了终端的安全性。
在阅读并理解了附图和详细描述后,可以明白其它方面。
附图概述
图1是本发明实施例的移动终端软件假界面识别方法的流程图;
图2是本发明实施例的移动终端软件假界面识别方法一种可选方案的流程图;
图3是本发明实施例的移动终端软件假界面识别方法的例子的流程图;
图4是本发明实施例的移动终端软件假界面识别装置的结构示意图;
图5是本发明实施例的移动终端软件假界面识别装置一种可选方案的结构示意图。
本发明的实施方式
需要说明的是,在不冲突的情况下,本申请中的实施例及实施例中的特征可以相互任意组合。
为了解决相关技术中智能手机上伪装软件欺诈的问题,本发明实施例提供了一种移动终端软件假界面识别方法及装置。
方法实施例
本发明实施例提供了一种移动终端软件假界面识别方法,图1是本发明实施例的移动终端软件假界面识别方法的流程图,如图1所示,根据本发明实施例的移动终端软件假界面识别方法包括如下步骤102~103:
步骤102,获取软件的UI截图,提取UI截图的图像特征信息以及UI截图上的软件附加信息;
步骤103,将UI截图的图像特征信息与图像特征库进行特征匹配,所述图像特征库中包括:软件用户界面UI的图像特征信息;在匹配成功的情况下,将UI截图的软件附加信息与附加特征库进行特征匹配,,所述附加特征库包括:除所述图像特征信息之外的软件附加信息;如果匹配不成功则确定所述UI截图为疑似伪装的假界面。
可选地,如果UI截图的软件附加信息与附加特征库匹配成功,则可以确定UI截图是正规界面。
本实施例的一种可选方案如图2所示,在步骤102前还可以包括:
步骤101,建立图像特征库和附加特征库。
可选地,图像特征库中的图像特征信息为:包括统计特征和原始像素特征的多层次特征向量集,所述统计特征包括:对图像的预定特征进行计算所得到的数值统计值,原始像素特征包括原始图像像素数据或经过图像大小调整和抽样处理的归一化像素数据;
附加特征库中的软件附加信息为:包括简单信息、和原始数据特征的多层次特征向量集,所述简单信息包括:软件基本信息,原始数据特征包括:软件深度信息。
可选地,在本发明实施例中,图像特征库包括:信任图像特征库、以及伪装图像特征库;附加特征库包括:信任附加特征库、以及伪装附加特征库。信任图像特征库中保存着信任软件的图像特征,伪装图像特征库中保存着伪装软件的图像特征,信任附加特征库保存着信任软件的附加特征,伪装附加特征库保存着伪装软件的附加特征。
需要说明的是,在本发明实施例中,上述软件可以为任何软件,为了更 好的保护用户的隐私,上述软件也可以为涉及用户隐私或理财类等常用高风险智能手机软件。
可选地,所述获取软件的UI截图包括:
在软件被启动运行时、软件运行过程中界面切换时、或包含敏感控件元素的界面被打开时,自动对相关界面进行截图,获取UI截图;或者,根据用户的调用,对用户当前显示的应用界面进行截图,获取UI截图。
在执行完步骤103之后,如果确定所述UI截图为疑似伪装的假界面,还可以对用户进行盗版软件的提醒。
可选地,所述方法还包括:
在UI截图的图像特征信息与图像特征库匹配失败的情况下,根据用户的选择,将UI截图的图像特征信息添加到图像特征库,并将UI截图的软件附加信息添加到附加特征库,如果用户不添加则可以结束操作。
可选地,在步骤103中,将UI截图的图像特征信息与图像特征库进行特征匹配包括:将UI截图的图像特征信息与伪装图像特征库进行特征匹配,如果匹配失败,则将UI截图的图像特征信息与信任图像特征库继续进行特征匹配;
在步骤103中,将UI截图的软件附加信息与附加特征库进行特征匹配包括:将UI截图的软件附加信息与伪装附加特征库进行特征匹配,如果匹配失败,则将UI截图的软件附加信息与信任附加特征库继续进行特征匹配。
可选地,在步骤103中,所述将UI截图的图像特征信息与图像特征库进行特征匹配包括:
将UI截图的图像特征信息中的统计特征与图像特征库中的统计特征进行匹配,在统计特征的匹配度小于第一预定阈值的情况下,确认特征匹配失败,在统计特征的匹配度大于或等于第一预定阈值的情况下,对所述UI截图的图像特征信息中的原始像素特征与所述所述图像特征库中的原始像素特征进行相关计算、和匹配,如果原始像素特征的匹配度大于或等于第二预定阈值,则确认特征匹配成功,如果原始像素特征的匹配度小于第二预定阈值则确认特征匹配失败;
所述将UI截图的软件附加信息与附加特征库进行特征匹配包括:
将UI截图的软件附加信息中的简单信息与附加特征库中的简单信息进行匹配,在简单信息的匹配度小于第三预定阈值的情况下,确认特征匹配失败,在简单信息的匹配度大于或等于第三预定阈值的情况下,将所述UI截图的软件附加信息中的原始数据特征与所述附加特征库中的原始数据特征进行匹配进行相关计算、和匹配,如果原始数据特征的匹配度大于或等于第四预定阈值,则确认特征匹配成功,如果原始数据特征的匹配度小于第四预定阈值确认特征匹配失败。
可选地,所述方法还可以包括:获取用户反馈的软件用户界面UI的图像特征信息和软件附加信息,并对图像特征库和附加特征库进行更新,从而不断完善图像特征库和附加特征库;可以但不限于通过互联网获取用户反馈。
本发明实施例的一个例子中,预先对涉及用户隐私或理财类等常用高风险智能手机软件建立图像特征库以及包含图像特征外其他信息的附加特征库。当某个软件被启动运行时、运行过程中界面切换时或包含敏感控件元素的界面被打开时等场景,对其相关界面进行截图,并对截图提取图像特征信息。对截图的图像特征信息与预先建立的图像特征库的信息进行比对,若匹配则疑似正规界面或钓鱼假界面,再通过附加特征库进行辨别,若匹配则说明是正版软件界面不作处理,若图像特征匹配但附加特征不匹配,则说明很可能是钓鱼的假界面,此时提示用户当前界面疑似钓鱼假界面。
此外,图像特征库和附加特征库可以预先建立部分样本,在运行过程中,图像特征库和附加特征库可在用户使用过程中可根据用户的操作和判断进一步完善和扩充。
可选地,在特征匹配时,对图像特征及附加特征进行提取时可建立多层次特征向量集,其中一些初步的统计值或直接的简单特征用于特征提取时进行快速比对粗选,而对一些原始抽样数据特征,将特征库中的原始数据与应用软件的相关数据相关计算,进行深度特征匹配。这种多层次特征向量特征匹配方式可显著提高防钓鱼界面识别的计算效率。
以下结合附图,本发明实施例的一个例子进行详细说明。
图3是本发明实施例的移动终端软件假界面识别方法的例子的流程图,如图3所示,包括如下步骤1~4:
步骤1,预先对涉及用户隐私或理财类等常用高风险智能手机软件建立包含一定样本数的UI界面图像特征库和图像信息外的附加特征库。图像特征库包含的信息能区分图像的常用的图像特征信息,包括但不限于归一化的图像亮度、色彩、纹理、边缘、焦点、线条、直方图、灰度图等。图像信息外的附加特征库包含的软件附加信息包括但不限于软件名称、版本信息、签名信息、文件字节码抽样特征等其它能附加信息。
对于图像特征库样本的图像特征信息,一种典型的实施方式是建立包含统计特征和原始像素特征的多层次特征向量集。统计特征是指对图像的某些特征进行计算,得到直接、简单的数值统计值,例如多个颜色分量在多个个区间段的分布比率、图像特定局部空间位置或全域像素灰度值的均值、方差等;原始像素特征是指对图像进行特定的归一化、抽样等简单处理后直接存储相关像素数据。统计特征用于后续特征比对时与应用软件截图进行快速比对粗步筛选,而原始像素特征用于后续特征比对时与应用软件截图进行相关计算深度匹配。
对于图像信息外的附加特征库,一种典型的实施方式可采用类似上面图像特征库的方式,建立包含简单信息、和原始数据特征的多层次特征向量集。简单信息包括软件名称、版本信息、文件大小等粗略信息,原始数据特征包括签名文件、字节码抽样信息的数据。简单信息用于应用软件进行快速比,原始数据特征用于与应用软件进行相关计算深度匹配。
步骤2,当监控到应用软件界面被打开运行时,对该软件的UI界面进行截图,并提取截图的图像特征信息以及界面本身的其它附加信息。图像特征信息和附加信息提取的参数类型完全参照步骤1所述的相关特征信息。由于手机应用软件通常包含多个界面,在界面切换也可重新截图,按步骤3启动新的图像特征匹配。此外,也可自动检测系软件界面控件属性,只对包含有密码输入框、付款字符等敏感属性的界面才启动截图和图像特征匹配。对于同一软件运行过程中可能涉及界面的切换的重新截图等场景,如之前已对相同界面进行过特征截图和识别,则直接根据上一次鉴别结果得到判断结论, 而不需要重新截图和识别。
步骤3,对截图的图像特征信息与图像特征库的图像特征信息进行图像特征匹配,如匹配成功,界面本身可能是正规软件,也可能是钓鱼假界面,则执行步骤4;若匹配不成功,则图像特征库本身不包含该界面匹配的图像特征信息,此时如用户选择手动添加进特征库,则将该界面提取到的图像特征信息添加进图像特征库,还可以将该软件的软件附加信息添加进附加信息库,从而进一步完善库信息,如用户不添加,则结束本次监控。
对于图像特征的匹配,典型实施方式是基于步骤1的多层次特征向量集的方式,先对统计特征等简单信息进行快速匹配用于初选,在初选满足匹配相似度的前提下,再对软件截图的原始像素特征与图像特征库每个样本的原始像素特征进行相关计算,进而精确的计算出相似度。统计特征只是对图像自身进行计算得到一个数值统计结果,图像特征库中的数据在与应用软件截图进行比对是只是直接的数值比较即可,而原始像素特征在匹配时需要与应用软件截图的相关特征进行相关计算,例如双方直接的像素差、方差、相关系数、PSNR、品质因数等。
步骤4,对界面涉及的软件附加信息与附加信息库进行匹配,若匹配成功,说明该界面是正规界面,结束监控;如果匹配不成功,则该界面为疑似伪装的假界面,对用户进行伪装假界面/钓鱼界面的提醒。对于同一软件运行过程中可能涉及界面的切换的重新截图的场景,如之前已经进行过附加信息识别,则直接根据上一次鉴别结果得到判断结论,而不需要重新识别。
对于附加信息的匹配,典型实施方式是基于步骤1的多层次特征向量集的方式,先对简单信息进行快速匹配用于初选,在初选满足匹配相似度的前提下,再对软件的原始数据特征与特征库每个样本的原始数据特征进行相关计算,进而精确的计算出相似度。
在本发明实施例中,图像特征库和附加信息库可通过联网的方式并结合海量的用户反馈操作进行不断的更新和完善。图像特征库和附加特征库本身也可再区分为信任特征库和伪装(恶意)特征库,在进行识别时,对恶意特征库可提高优先顺序进行先期比对以加快匹配速度。
此外,本发明实施例是在监控到手机应用软件启动运行后自动进行截图 检测的,在实际实施时也可以特定的UI展现方式,例如以悬浮窗按钮、手机系统控件、系统特定按键响应、语音指令等方式让用户显示的对应用界面进行防伪装鉴别,而不启用自动特征鉴别功能,这样检测效率更高,对于多界面切换的应用来说也不存在冗余截图的问题。
综上所述,本发明实施例以界面截图的图像特征为主要的识别依据,并结合界面外的其他附加信息进一步判断界面是否为疑似假界面。本发明实施例的技术方案至少部分解决了目前经常出现的钓鱼假界面,非法获取用户诸如银行卡密码、个人身份隐私数据等问题。基于本发明实施例的安全类软件具有重要的实用价值和广阔的应用前景。
本发明实施例还提供了一种计算机可读存储介质,存储有计算机可执行指令,所述计算机可执行指令用于执行上述方法。
装置实施例
根据本发明的实施例,提供了一种移动终端软件假界面识别装置,图4是本发明实施例的移动终端软件假界面识别装置的结构示意图,如图4所示,根据本发明实施例的移动终端软件假界面识别装置包括:提取模块32以及匹配模块34。
所述提取模块32设置成获取软件的UI截图,提取UI截图的图像特征信息以及UI截图上的软件附加信息;
所述匹配模块34设置成将UI截图的图像特征信息与图像特征库进行特征匹配,图像特征库中包括:软件用户界面UI的图像特征信息;在匹配成功的情况下,将UI截图的软件附加信息与附加特征库进行特征匹配,附加特征库包括:除图像特征信息之外的软件附加信息;如果匹配不成功则确定所述UI截图为疑似伪装的假界面。
可选地,如果UI截图的软件附加信息与附加特征库匹配成功,则可以确定UI截图是正规界面。
本实施例的一种可选方案如图5所示,所述装置还可以包括:
建立模块30,设置成建立图像特征库和附加特征库。
可选地,所述图像特征库包括:信任图像特征库、以及伪装图像特征库; 附加特征库包括:信任附加特征库、以及伪装附加特征库。
可选地,所述图像特征库中的图像特征信息为:包括统计特征和原始像素特征的多层次特征向量集,其中,统计特征包括:对图像的预定特征进行计算所得到的数值统计值,原始像素特征包括原始图像像素数据或经过图像大小调整和抽样处理的归一化像素数据;所述附加特征库中的软件附加信息为:包括简单信息、和原始数据特征的多层次特征向量集,其中,简单信息包括:软件基本信息,原始数据特征包括:软件深度信息。
可选地,所述提取模块32获取软件的UI截图包括:
所述提取模块32在软件被启动运行时、软件运行过程中界面切换时、或包含敏感控件元素的界面被打开时,自动对相关界面进行截图,获取UI截图;或者,所述提取模块根据用户的调用,对用户当前显示的应用界面进行截图,获取UI截图。
可选地,所述匹配模块34还可以设置成在确定UI截图为疑似伪装的假界面后,对用户进行盗版软件的提醒。
可选地,所述匹配模块34将UI截图的图像特征信息与所述图像特征库进行特征匹配包括:
所述匹配模块34将UI截图的图像特征信息与伪装图像特征库进行特征匹配,如果匹配失败,则将UI截图的图像特征信息与信任图像特征库继续进行特征匹配;
所述匹配模块34将UI截图的软件附加信息与所述附加特征库进行特征匹配包括:
将UI截图的软件附加信息与伪装附加特征库进行特征匹配,如果匹配失败,则将UI截图的软件附加信息与信任附加特征库继续进行特征匹配。
可选地,所述匹配模块34将UI截图的图像特征信息与所述图像特征库进行特征匹配包括:
所述匹配模块34将UI截图的图像特征信息中的统计特征与图像特征库中的统计特征进行匹配,在统计特征的匹配度小于第一预定阈值的情况下,确认特征匹配失败,在统计特征的匹配度大于或等于第一预定阈值的情况下, 对所述UI截图的图像特征信息中的原始像素特征与所述所述图像特征库中的原始像素特征进行相关计算、和匹配,如果原始像素特征的匹配度大于或等于第二预定阈值,则确认特征匹配成功,如果原始像素特征的匹配度小于第二预定阈值则确认特征匹配失败。
可选地,所述匹配模块34将UI截图的软件附加信息与所述附加特征库进行特征匹配包括:
所述匹配模块34将UI截图的软件附加信息中的简单信息与附加特征库中的简单信息进行匹配,在简单信息的匹配度小于第三预定阈值的情况下,确认特征匹配失败,在简单信息的匹配度大于或等于第三预定阈值的情况下,将所述UI截图的软件附加信息中的原始数据特征与所述附加特征库中的原始数据特征进行匹配进行相关计算、和匹配,如果原始数据特征的匹配度大于或等于第四预定阈值,则确认特征匹配成功,如果原始数据特征的匹配度小于第四预定阈值则确认特征匹配失败。
可选地,上述装置还可以包括:
添加模块,设置成在UI截图的图像特征信息与图像特征库匹配失败的情况下,根据用户的选择,将UI截图的图像特征信息添加到图像特征库,并将UI截图的软件附加信息添加到附加特征库,如果用户不添加则可以结束操作。
可选地,上述装置还可以包括:
更新模块,设置成获取用户反馈的软件用户界面UI的图像特征信息和软件附加信息,并对图像特征库和附加特征库进行更新,从而不断完善图像特征库和附加特征库;所述更新模块可以但不限于通过互联网获取用户反馈。
本发明实施例每个模块的处理细节可以参照方法实施例的相关描述进行理解,在此不再赘述。
本发明实施例的技术方案通过将图像特征库以及包含图像特征外其他信息的附加特征库与软件相关界面的截图进行对比,来判断是否为疑似假界面,缓解了现有技术中智能手机上伪装软件欺诈的问题,能够快速的对钓鱼软件进行识别,提高了用户手机的安全性。
在此提供的算法和显示不与任何特定计算机、虚拟系统或者其它设备固 有相关。多种通用系统也可以与基于在此的示教一起使用。根据上面的描述,构造这类系统所要求的结构是显而易见的。此外,本发明实施例也不针对任何特定编程语言。应当明白,可以利用各种编程语言实现在此描述的本发明实施例的内容,并且上面对特定语言所做的描述是为了披露本发明实施例的实施方式。
本领域那些技术人员可以理解,可以对实施例中的客户端中的模块进行自适应性地改变并且把它们设置在与该实施例不同的一个或多个客户端中。可以把实施例中的模块组合成一个模块,以及此外可以把它们分成多个子模块或子单元或子组件。除了这样的特征和/或过程或者单元中的至少一些是相互排斥之外,可以采用任何组合对本说明书(包括伴随的权利要求、摘要和附图)中公开的所有特征以及如此公开的任何方法或者客户端的所有过程或单元进行组合。除非另外明确陈述,本说明书(包括伴随的权利要求、摘要和附图)中公开的每个特征可以由提供相同、等同或相似目的的替代特征来代替。
本发明的每个部件实施例可以以硬件实现,或者以在一个或者多个处理器上运行的软件模块实现,或者以它们的组合实现。本领域的技术人员应当理解,可以在实践中使用微处理器或者数字信号处理器(DSP)来实现根据本发明实施例的加载有排序网址的客户端中的一些或者全部部件的一些或者全部功能。本发明实施例还可以实现为用于执行这里所描述的方法的一部分或者全部的设备或者装置程序(例如,计算机程序和计算机程序产品)。这样的实现本发明实施例的程序可以存储在计算机可读介质上,或者可以具有一个或者多个信号的形式。这样的信号可以从因特网网站上下载得到,或者在载体信号上提供,或者以任何其他形式提供。
应该注意本领域技术人员在不脱离所附权利要求的范围的情况下可设计出替换实施例。单词“包含”不排除存在未列在权利要求中的元件或步骤。位于元件之前的单词“一”或“一个”不排除存在多个这样的元件。本发明实施例可以借助于包括有不同元件的硬件以及借助于适当编程的计算机来实现。在列举了一个或多个装置的单元权利要求中,这些装置中的一个或多个可以是通过同一个硬件项来体现。单词“第一”、“第二”、以及“第三”等的使 用不表示任何顺序。可将这些单词解释为名称。
工业实用性
本发明实施例通过建立图像特征库以及包含图像特征外其他信息的附加特征库与软件相关界面的截图进行对比来判断是否为疑似假界面,可以缓解相关技术中智能手机上伪装软件欺诈的问题,能够快速的对钓鱼软件进行识别,提高了终端的安全性。

Claims (14)

  1. 一种移动终端软件假界面识别方法,包括:
    获取软件的UI截图,提取所述UI截图的图像特征信息以及所述UI截图上的软件附加信息;
    将所述UI截图的图像特征信息与所述图像特征库进行特征匹配,所述图像特征库中包括:软件用户界面UI的图像特征信息;在匹配成功的情况下,将所述UI截图的软件附加信息与所述附加特征库进行特征匹配,所述附加特征库包括:除所述图像特征信息之外的软件附加信息;如果匹配不成功则确定所述UI截图为疑似伪装的假界面。
  2. 如权利要求1所述的方法,其中,所述获取软件的UI截图前还包括:建立所述图像特征库和附加特征库。
  3. 如权利要求1所述的方法,还包括:
    在所述UI截图的图像特征信息与所述图像特征库匹配失败的情况下,根据用户的选择,将所述UI截图的图像特征信息添加到所述图像特征库,并将所述UI截图的软件附加信息添加到所述附加特征库。
  4. 如权利要求1所述的方法,其中,所述获取软件的UI截图包括:
    在软件被启动运行时、软件运行过程中界面切换时、或包含敏感控件元素的界面被打开时,自动对相关界面进行截图,获取所述UI截图;或者,
    根据用户的调用,对用户当前显示的应用界面进行截图,获取所述UI截图。
  5. 如权利要求1所述的方法,其中,所述图像特征库包括:信任图像特征库、以及伪装图像特征库;所述附加特征库包括:信任附加特征库、以及伪装附加特征库;
    所述将UI截图的图像特征信息与所述图像特征库进行特征匹配包括:
    将所述UI截图的图像特征信息与所述伪装图像特征库进行特征匹配,如果匹配失败,则将所述UI截图的图像特征信息与所述信任图像特征库继续进行特征匹配;
    所述将UI截图的软件附加信息与所述附加特征库进行特征匹配包括:
    将所述UI截图的软件附加信息与所述伪装附加特征库进行特征匹配,如果匹配失败,则将所述UI截图的软件附加信息与所述信任附加特征库继续进行特征匹配。
  6. 如权利要求1或5所述的方法,其中,所述图像特征库中的图像特征信息为:包括统计特征和原始像素特征的多层次特征向量集,所述统计特征包括:对图像的预定特征进行计算所得到的数值统计值,所述原始像素特征包括:原始图像像素数据或经过图像大小调整和抽样处理的归一化像素数据;
    所述附加特征库中的软件附加信息为:包括简单信息、和原始数据特征的多层次特征向量集,其中,所述简单信息包括:软件基本信息,所述原始数据特征包括:软件深度信息;
    所述将UI截图的图像特征信息与所述图像特征库进行特征匹配包括:
    将所述UI截图的图像特征信息中的统计特征与所述图像特征库中的统计特征进行匹配,在统计特征的匹配度小于第一预定阈值的情况下,确认特征匹配失败,在统计特征的匹配度大于或等于第一预定阈值的情况下,对所述UI截图的图像特征信息中的原始像素特征与所述所述图像特征库中的原始像素特征进行相关计算、和匹配,如果原始像素特征的匹配度大于或等于第二预定阈值,则确认特征匹配成功,如果原始像素特征的匹配度小于第二预定阈值则确认特征匹配失败;
    所述将UI截图的软件附加信息与所述附加特征库进行特征匹配包括:
    将所述UI截图的软件附加信息中的简单信息与所述附加特征库中的简单信息进行匹配,在简单信息的匹配度小于第三预定阈值的情况下,确认特征匹配失败,在简单信息的匹配度大于或等于第三预定阈值的情况下,将所述UI截图的软件附加信息中的原始数据特征与所述附加特征库中的原始数据特征进行匹配进行相关计算、和匹配,如果原始数据特征的匹配度大于或等于第四预定阈值,则确认特征匹配成功,如果原始数据特征的匹配度小于第四预定阈值则确认特征匹配失败。
  7. 如权利要求1所述的方法,还包括:
    获取用户反馈的UI的图像特征信息和软件附加信息,并对所述图像特征库和所述附加特征库进行更新。
  8. 一种移动终端软件假界面识别装置,包括:
    提取模块,设置成获取软件的UI截图,提取所述UI截图的图像特征信息以及所述UI截图上的软件附加信息;
    匹配模块,设置成将所述UI截图的图像特征信息与所述图像特征库进行特征匹配,所述图像特征库中包括:软件用户界面UI的图像特征信息;在匹配成功的情况下,将所述UI截图的软件附加信息与所述附加特征库进行特征匹配,所述附加特征库包括:除所述图像特征信息之外的软件附加信息;如果匹配不成功则确定所述UI截图为疑似伪装的假界面。
  9. 如权利要求8所述的装置,还包括:建立模块,设置成建立图像特征库和附加特征库。
  10. 如权利要求8所述的装置,还包括:
    添加模块,设置成在所述UI截图的图像特征信息与所述图像特征库匹配失败的情况下,根据用户的选择,将所述UI截图的图像特征信息添加到所述图像特征库,并将所述UI截图的软件附加信息添加到所述附加特征库,如果用户不添加则结束操作。
  11. 如权利要求8所述的装置,其中,所述提取模块获取软件的UI截图包括:
    所述提取模块在软件被启动运行时、软件运行过程中界面切换时、或包含敏感控件元素的界面被打开时,自动对相关界面进行截图,获取所述UI截图;或者,
    所述提取模块根据用户的调用,对用户当前显示的应用界面进行截图,获取所述UI截图。
  12. 如权利要求8所述的装置,其中,所述图像特征库包括:信任图像特征库、以及伪装图像特征库;所述附加特征库包括:信任附加特征库、以及伪装附加特征库;
    所述匹配模块将UI截图的图像特征信息与所述图像特征库进行特征匹 配包括:
    所述匹配模块将所述UI截图的图像特征信息与所述伪装图像特征库进行特征匹配,如果匹配失败,则将所述UI截图的图像特征信息与所述信任图像特征库继续进行特征匹配;
    所述匹配模块将所述UI截图的软件附加信息与所述附加特征库进行特征匹配包括:
    所述匹配模块将所述UI截图的软件附加信息与所述伪装附加特征库进行特征匹配,如果匹配失败,则将所述UI截图的软件附加信息与所述信任附加特征库继续进行特征匹配。
  13. 如权利要求8或12所述的装置,其中,所述图像特征库中的图像特征信息为:包括统计特征和原始像素特征的多层次特征向量集,所述统计特征包括:对图像的预定特征进行计算所得到的数值统计值,所述原始像素特征包括原始图像像素数据或经过图像大小调整和抽样处理的归一化像素数据;
    所述附加特征库中的软件附加信息为:包括简单信息、和原始数据特征的多层次特征向量集,所述简单信息包括:软件基本信息,所述原始数据特征包括:软件深度信息;
    所述匹配模块将UI截图的图像特征信息与所述图像特征库进行特征匹配包括:
    将所述UI截图的图像特征信息中的统计特征与所述图像特征库中的统计特征进行匹配,在统计特征的匹配度小于第一预定阈值的情况下,确认特征匹配失败,在统计特征的匹配度大于或等于第一预定阈值的情况下,对所述UI截图的图像特征信息中的原始像素特征与所述所述图像特征库中的原始像素特征进行相关计算、和匹配,如果原始像素特征的匹配度大于或等于第二预定阈值,则确认特征匹配成功,如果原始像素特征的匹配度小于第二预定阈值则确认特征匹配失败;
    将所述UI截图的软件附加信息中的简单信息与所述附加特征库中的简单信息进行匹配,在简单信息的匹配度小于第三预定阈值的情况下,确认特 征匹配失败,在简单信息的匹配度大于或等于第三预定阈值的情况下,将所述UI截图的软件附加信息中的原始数据特征与所述附加特征库中的原始数据特征进行匹配进行相关计算、和匹配,如果原始数据特征的匹配度大于或等于第四预定阈值,则确认特征匹配成功,如果原始数据特征的匹配度小于第四预定阈值则确认特征匹配失败。
  14. 如权利要求8所述的装置,还包括:
    更新模块,设置成获取用户反馈的UI的图像特征信息和软件附加信息,并对所述图像特征库和所述附加特征库进行更新。
PCT/CN2016/079922 2015-11-27 2016-04-21 移动终端软件假界面识别方法及装置 WO2016197710A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510848982.4 2015-11-27
CN201510848982.4A CN106815522A (zh) 2015-11-27 2015-11-27 移动终端软件假界面识别方法及装置

Publications (1)

Publication Number Publication Date
WO2016197710A1 true WO2016197710A1 (zh) 2016-12-15

Family

ID=57503088

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/079922 WO2016197710A1 (zh) 2015-11-27 2016-04-21 移动终端软件假界面识别方法及装置

Country Status (2)

Country Link
CN (1) CN106815522A (zh)
WO (1) WO2016197710A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108133137A (zh) * 2017-12-13 2018-06-08 北京奇虎科技有限公司 智能终端中的界面安全性检测方法和装置
CN108416192A (zh) * 2018-03-01 2018-08-17 中国工商银行股份有限公司 一种检测假冒企业应用程序的装置及方法
CN109815100A (zh) * 2019-01-04 2019-05-28 深圳市象形字科技股份有限公司 一种利用图像对比分析对叫号宝软件的行为监控方法
CN111143188A (zh) * 2018-11-02 2020-05-12 中移(杭州)信息技术有限公司 一种对应用进行自动化测试的方法及设备

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109426830B (zh) * 2017-08-29 2022-05-17 武汉安天信息技术有限责任公司 一种自动识别移动终端场景的方法和装置
CN108108618B (zh) * 2017-12-28 2021-05-25 中国信息通信研究院 伪造攻击的应用界面检测方法及装置
CN108154031B (zh) * 2018-01-17 2021-08-06 腾讯科技(深圳)有限公司 伪装应用程序的识别方法、装置、存储介质和电子装置
CN109151423B (zh) * 2018-10-31 2021-03-30 歌尔光学科技有限公司 投影机及其甄别方法、装置、信息添加方法和存储介质
CN110505497B (zh) * 2019-07-31 2022-04-22 湖南微算互联信息技术有限公司 一种云手机运行监测方法、系统、装置和存储介质
CN112988283A (zh) * 2021-05-12 2021-06-18 鹏城实验室 截图获得方法、装置、终端设备以及存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103530561A (zh) * 2013-10-21 2014-01-22 北京奇虎科技有限公司 防止木马程序基于社会工程学攻击方法和装置
CN103699843A (zh) * 2013-12-30 2014-04-02 珠海市君天电子科技有限公司 一种恶意行为检测方法及装置
CN104657665A (zh) * 2015-03-12 2015-05-27 四川神琥科技有限公司 一种文件处理方法
CN105095751A (zh) * 2014-05-07 2015-11-25 中兴软创科技股份有限公司 一种面向Android平台的钓鱼恶意应用检测方法

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103685307B (zh) * 2013-12-25 2017-08-11 北京奇虎科技有限公司 基于特征库检测钓鱼欺诈网页的方法及系统、客户端、服务器
CN104143008B (zh) * 2014-08-11 2017-10-27 北京奇虎科技有限公司 基于图片匹配检测钓鱼网页的方法及装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103530561A (zh) * 2013-10-21 2014-01-22 北京奇虎科技有限公司 防止木马程序基于社会工程学攻击方法和装置
CN103699843A (zh) * 2013-12-30 2014-04-02 珠海市君天电子科技有限公司 一种恶意行为检测方法及装置
CN105095751A (zh) * 2014-05-07 2015-11-25 中兴软创科技股份有限公司 一种面向Android平台的钓鱼恶意应用检测方法
CN104657665A (zh) * 2015-03-12 2015-05-27 四川神琥科技有限公司 一种文件处理方法

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108133137A (zh) * 2017-12-13 2018-06-08 北京奇虎科技有限公司 智能终端中的界面安全性检测方法和装置
CN108133137B (zh) * 2017-12-13 2021-11-23 北京奇虎科技有限公司 智能终端中的界面安全性检测方法和装置
CN108416192A (zh) * 2018-03-01 2018-08-17 中国工商银行股份有限公司 一种检测假冒企业应用程序的装置及方法
CN111143188A (zh) * 2018-11-02 2020-05-12 中移(杭州)信息技术有限公司 一种对应用进行自动化测试的方法及设备
CN111143188B (zh) * 2018-11-02 2023-09-22 中移(杭州)信息技术有限公司 一种对应用进行自动化测试的方法及设备
CN109815100A (zh) * 2019-01-04 2019-05-28 深圳市象形字科技股份有限公司 一种利用图像对比分析对叫号宝软件的行为监控方法
CN109815100B (zh) * 2019-01-04 2022-06-28 深圳市象形字科技股份有限公司 一种利用图像对比分析对叫号宝软件的行为监控方法

Also Published As

Publication number Publication date
CN106815522A (zh) 2017-06-09

Similar Documents

Publication Publication Date Title
WO2016197710A1 (zh) 移动终端软件假界面识别方法及装置
US10805346B2 (en) Phishing attack detection
US11405386B2 (en) Electronic device for authenticating user and operating method thereof
WO2016197765A1 (zh) 人脸识别方法及识别系统
US11165793B2 (en) Method and system for detecting credential stealing attacks
US9503474B2 (en) Identification of trusted websites
WO2016015680A1 (zh) 移动终端输入窗口的安全检测方法和安全检测装置
WO2015085871A1 (zh) 移动终端防盗方法及客户端
JP6580783B2 (ja) 人物再識別システム及び方法
US10389710B2 (en) Method and system for extracting characteristic information
CN111385270A (zh) 基于waf的网络攻击检测方法及装置
TW201944294A (zh) 身份驗證方法和裝置、電子裝置、電腦程式和儲存介質
WO2019184140A1 (zh) 基于vr的应用程序打开方法、电子装置、设备及存储介质
CN116366338B (zh) 一种风险网站识别方法、装置、计算机设备及存储介质
EP3510557B1 (en) Image processing system for verification of rendered data
CN114448664A (zh) 钓鱼网页的识别方法、装置、计算机设备及存储介质
US20200026866A1 (en) Method and device for covering private data
US20180124034A1 (en) Image based method, system and computer program product to authenticate user identity
WO2016095671A1 (zh) 一种应用程序的消息处理方法和装置
WO2016180211A1 (zh) 一种伪装应用的处理方法和装置
WO2017041358A1 (zh) 一种用户身份识别方法、装置和移动终端
KR102408489B1 (ko) Ip 기반 보안 관제 방법 및 그 시스템
EP3678041A1 (en) Apparatus and method for camera-based user authentication for content access
US10764301B2 (en) Method and system for user authentication based on a visual representation of user location
Bunzel et al. Cover-aware steganalysis

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16806608

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 16806608

Country of ref document: EP

Kind code of ref document: A1