Phishing website detection method, detection device, processing method and processing device
By identifying, feature extraction and calculating similarity, and closing and intercepting, the problem of single detection and poor timeliness in the existing technology is solved, efficient detection and disposal of phishing websites is achieved, and user security is improved.
Patent Information
- Application Number
- CN202411034549.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-31
- Publication Date
- 2024-11-15
AI Technical Summary
The existing phishing website has a single detection path and poor timeliness, and it is impossible to achieve an effective closed loop from detection to disposal, resulting in threatening the safety of user property.
By identifying the target website, collecting suspected phishing websites, extracting behavioral characteristics, calculating feature similarity, determining whether it is a phishing website, and shutting down, blocking and access blocking of detected phishing websites.
Multi-dimensional detection has been realized, the early detection and timely disposal of phishing websites has been improved, the security of users' access to the website has been improved, and an effective closed loop from discovery to disposal is formed.
Smart Images

Figure CN118972117A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of computer security technology, and in particular to a phishing website detection method, a detection device, a processing method, and a processing device. Background Art
[0002] Phishing websites are fake websites that deceive users. They are also the most common form of fraud on the Internet. They are usually disguised as banks and e-commerce websites that steal private information such as bank accounts and passwords submitted by users. Phishing websites usually take advantage of victims' trust in regular websites and set up domain names and page styles similar to real websites to confuse users. Once users enter personal information on phishing websites, they may face risks such as account theft and property loss. Therefore, it is very important to efficiently detect phishing websites and deal with them in a timely manner to protect users' property safety.
[0003] Currently, the existing methods of detecting phishing websites are relatively simple, the detection timeliness is also weak, and there is a lack of disposal links. After the phishing websites are detected, it is impossible to deal with them in a timely manner. Summary of the invention
[0004] The present disclosure provides a phishing website detection method, a detection device, a processing method and a processing device, an electronic device, and a storage medium.
[0005] According to a first aspect of the present disclosure, a phishing website detection method is provided, comprising:
[0006] Identify target websites and collect suspected phishing websites among the target websites;
[0007] Extracting features of the suspected phishing website to obtain one or more behavioral features;
[0008] Based on one or more of the behavioral features, calculate the feature similarity corresponding to the suspected phishing website;
[0009] Determine whether the suspected phishing website is a phishing website based on the feature similarity.
[0010] According to a second aspect of the present disclosure, a method for processing a phishing website is provided, comprising:
[0011] Obtaining the domain name or IP address of the phishing website detected by the phishing website detection method described in any one of the above technical solutions;
[0012] Process the domain name or IP address of the phishing site; wherein the processing includes at least one of the following: shutting down the phishing website; intercepting phishing text messages sent by the phishing website; blocking access to the phishing website.
[0013] According to a third aspect of the present disclosure, a phishing website detection device is provided, comprising:
[0014] an identification module, configured to identify target websites and collect suspected phishing websites from the target websites;
[0015] A feature extraction module is configured to extract features from the suspected phishing website to obtain one or more behavior features;
[0016] A calculation module, configured to calculate a feature similarity corresponding to the suspected phishing website based on one or more of the behavior features;
[0017] The determination module is configured to determine whether the suspected phishing website is a phishing website based on the feature similarity.
[0018] According to a fourth aspect of the present disclosure, a phishing website processing device is provided, comprising:
[0019] An acquisition module is configured to acquire the domain name or IP address of the phishing website detected by the phishing website detection method described in any one of the above technical solutions;
[0020] The processing module is configured to process the domain name or IP address of the phishing site; wherein the processing includes at least one of the following: shutting down the phishing website; intercepting phishing text messages sent by the phishing website; and blocking access to the phishing website.
[0021] According to a fifth aspect of the present disclosure, there is provided an electronic device, including:
[0022] at least one processor; and
[0023] a memory communicatively connected to the at least one processor; wherein,
[0024] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute any method in any of the above technical solutions.
[0025] According to a sixth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute any one of the methods described in the above technical solutions.
[0026] According to a seventh aspect of the present disclosure, a computer program product is provided, including a computer program, wherein the computer program implements any one of the methods described in the above technical solutions when executed by a processor.
[0027] The present disclosure provides a phishing website detection method and a detection device, which perform detection through multiple detection dimensions and have strong timeliness, and can promptly discover phishing websites in the early stages of phishing website propagation; a corresponding phishing website processing method is provided to achieve an effective closed loop from discovery to disposal, thereby improving the security of user access to websites.
[0028] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0029] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.
[0030] Figure 1 is a schematic diagram of the steps of the phishing website detection method in an embodiment of the present disclosure;
[0031] Figure 2 is a schematic diagram of the steps of the method for processing phishing websites in an embodiment of the present disclosure;
[0032] Figure 3 is a principle block diagram of a phishing website detection device in an embodiment of the present disclosure;
[0033] Figure 4 is a principle block diagram of a phishing website processing device in an embodiment of the present disclosure;
[0034] Figure 5 is a block diagram of the phishing website detection and processing system of the present disclosure; Figure 6 It is a block diagram of an electronic device used to implement the phishing website detection method or phishing website processing method of the embodiment of the present disclosure. DETAILED DESCRIPTION
[0035] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.
[0036] In order to solve the technical problems of the prior art such as single detection method, poor detection timeliness, and inability to achieve closed-loop disposal, the present disclosure provides a phishing website detection method, such as Figure 1 As shown, including:
[0037] Step S101, identifying target websites and collecting suspected phishing websites among the target websites;
[0038] Step S102, extracting features from suspected phishing websites to obtain one or more behavioral features;
[0039] Step S103, calculating the feature similarity corresponding to the suspected phishing website based on one or more behavior features;
[0040] Step S104, determining whether the suspected phishing website is a phishing website based on feature similarity.
[0041] Specifically, in step S101, the URLs of suspected phishing websites can be collected through multiple different channels, such as through DNS (Domain Name System) servers and phishing SMS collection, and domain names and IP addresses similar to historically identified phishing websites can be collected and identified as suspected phishing websites. Usually, phishing websites also have some characteristics. For example, the URLs of regular websites usually start with "http: / / " or "https: / / ", while the URLs of phishing websites may be relatively simple, or even contain only letters and numbers. In addition, the domain names of phishing websites are usually similar to those of regular websites, but there may be slight differences. Matching can be performed through historical detection records, and the URLs of suspected phishing websites from multiple channels can be collected to identify the domain names and IP addresses of suspected phishing websites.
[0042] In step S102 and step S103, feature extraction is performed on the collected suspected phishing websites, and the extracted behavioral features may include but are not limited to URL (uniform resource locator), page HTML (Hyper Text Markup) elements, HTTP (Hypertext Transfer Protocol) access features, etc. Then, based on the extracted behavioral features, the feature similarity with the identified phishing URLs is calculated.
[0043] In step S104, after calculating the feature similarity with the identified phishing website, if the feature similarity reaches a preset threshold, the suspected phishing website can be determined to be a phishing website. In this way, the collected suspected phishing websites can be accurately judged to reduce misidentification. After the rough identification in step S101, the suspected phishing website is accurately identified, which can reduce the identification coverage of phishing websites and improve the accuracy of identification.
[0044] As an optional implementation, step S101, identifying the target website, and collecting the suspected phishing websites in the target website includes at least one of the following:
[0045] (1) Perform domain name analysis on the target website through the domain name system server to obtain the IP address of the target website.
[0046] DNS server collection: When the domain name of a phishing website is accessed, DNS domain name resolution will be performed to obtain the real website IP address. The resolution record will be recorded by the DNS server responsible for resolution work. By analyzing the workplace network environment or the operator's DNS server resolution record, the domain name of the website IP address resolved by DNS is marked as a suspected phishing website domain name.
[0047] (2) Conduct batch detection of IP addresses of overseas public clouds to obtain IP addresses of suspected phishing websites.
[0048] Detection and collection of overseas public cloud IP addresses in the C segment: Since overseas public cloud service providers are more difficult to control than domestic cloud service providers, almost all phishing website servers are set up in overseas public clouds. Regular batch detection of overseas public cloud IPs is carried out, and phishing website IP addresses are identified through phishing website detection and analysis.
[0049] (3) Collect phishing text messages through different channels and extract the domain names of suspected phishing websites from the phishing text messages.
[0050] Phishing SMS collection: Phishing SMS are collected through customer service, offline feedback, operator feedback and other channels, and the domain names of suspected phishing websites are extracted from them.
[0051] (4) Perform association analysis on known phishing websites to obtain the domain names and IP addresses of suspected phishing sites associated with the known phishing websites.
[0052] As an optional implementation, performing domain name analysis on the target website through a domain name system server to obtain the IP address of the target website includes:
[0053] When accessing the target website, the domain name of the target website is resolved through the domain name system server to obtain the IP address of the target website;
[0054] The IP address of the target website is matched with the domain name of a known phishing site. If there is a match, it is marked as a suspected phishing website.
[0055] As an optional implementation, step S103, based on one or more behavioral features, calculating the feature similarity corresponding to the suspected phishing website includes:
[0056] A corresponding characteristic coefficient is set for each behavior characteristic; wherein the sum of multiple characteristic coefficients is 1;
[0057] The feature coefficients corresponding to multiple behavioral features are multiplied, and the results of the product operation are summed to obtain the feature similarity.
[0058] Specifically, it is currently found that the vast majority of phishing websites use several similar sets of website templates for rapid website construction. Therefore, for such phishing websites with obvious rule characteristics, a rule engine detection method is applicable. This method extracts one or more behavioral features X of the website (such as URL, page HTML elements, HTTP access features, etc.) as the judgment criteria of the rule engine. Different feature coefficients α are specified according to the strength of the behavioral characteristics (the relevance to the judgment of phishing websites), and the sum of multiple feature coefficients is 1; among them, the feature coefficient α is equivalent to the weight of each behavioral feature, and different weights are assigned according to the influence of each behavioral feature. Multiply multiple behavioral features X by the feature coefficient α and sum them to obtain the feature similarity R. The formula is as follows:
[0059]
[0060] In this embodiment, the collected suspected phishing websites are subjected to feature similarity calculation, and if the feature similarity exceeds a preset threshold, they are identified as phishing websites.
[0061] As an optional implementation, step S102, extracting features from suspected phishing websites to obtain one or more behavioral features includes:
[0062] Feature extraction is performed on suspected phishing websites to obtain one or more behavioral features of uniform resource locator features (URL), page markup language element features (page HTML elements), and hypertext transfer protocol access features (HTTP access features).
[0063] As an optional implementation, determining whether a suspected phishing website is a phishing website based on feature similarity includes:
[0064] The feature similarity is compared with the preset threshold, and if the feature similarity exceeds the preset threshold, it is identified as a phishing website. For example, if the feature similarity between a suspected phishing website and an identified phishing website reaches 60%, it can be determined to be a phishing website.
[0065] As an optional implementation, after step S104, based on feature similarity, determining whether the suspected phishing website is a phishing website, further includes:
[0066] Perform correlation analysis on the URLs that have been identified as phishing websites to obtain the associated suspected phishing websites;
[0067] Extracting features of the associated suspected phishing websites to obtain one or more second behavior features;
[0068] Based on the one or more second behavior features, calculate the second feature similarity corresponding to the associated suspected phishing website;
[0069] It is determined whether the associated suspected phishing website is a phishing website based on the second feature similarity.
[0070] Specifically, after detecting and confirming a phishing website, you can continue to detect websites associated with the phishing website, and also obtain the feature similarity of each associated website by calculating the feature similarity, and then determine whether the associated website is a phishing website. In this way, compared with traversing all target websites, the detection is more targeted, the associated phishing website can be detected quickly, and the detection timeliness is higher.
[0071] As an optional implementation manner, the URL of the phishing website includes the domain name and / or URL of the phishing website; performing association analysis on the URL that has been identified as the phishing website to obtain the associated suspected phishing website includes the following two methods:
[0072] (1) Perform association analysis on the domain names that have been identified as phishing websites to obtain associated suspected phishing websites.
[0073] (2) Perform association analysis on the IP addresses that have been identified as phishing websites to obtain associated suspected phishing websites.
[0074] Specifically, the domain name association analysis includes: obtaining the registration information of the phishing website, and querying the domain names registered at the same time or the historically registered domain names registered by the registrant based on the registration information, and classifying the domain names registered at the same time and the historically registered domain names as associated suspected phishing websites; obtaining the IP pointing information of the phishing website, and classifying the IP address pointed to by the IP pointing information as an associated suspected phishing website; obtaining the subdomain name of the phishing website, and classifying the subdomain name as an associated suspected phishing website; in response to the domain name of the phishing website being a wildcard domain name, the wildcard domain name is clipped to the next level, and the clipped second-level domain name is classified as an associated suspected phishing website; obtaining the adjacent domain names of the phishing website by recursively detecting the domain names constructed by frequency connection, and classifying the adjacent domain names as an associated suspected phishing website.
[0075] The IP address association analysis includes: obtaining the current associated domain name and the historical associated domain name associated with the IP address that has been identified as a phishing website, and classifying the current associated domain name and the historical associated domain name as associated suspected phishing websites; obtaining other IP addresses with the same C segment as the IP address that has been identified as a phishing website, and identifying the websites that are open to access as associated suspected phishing websites.
[0076] The present disclosure also provides a method for processing phishing websites, such as Figure 2 As shown, including:
[0077] Step S201, obtaining the domain name or IP address of a phishing website detected by the phishing website detection method described in any one of the above embodiments;
[0078] Step S202, processing the domain name or IP address of the phishing site; wherein the processing includes at least one of the following: shutting down the phishing website; intercepting phishing text messages sent by the phishing website; blocking access to the phishing website.
[0079] The present disclosure bans and blocks access to domain names or IP addresses that have been identified as phishing websites. Based on the links through which phishing websites spread, the banning strategies can be divided into the following three categories:
[0080] Shutdown of phishing websites: Block phishing websites at the source through the cloud service provider that owns the IP address of the phishing website.
[0081] Phishing SMS interception: Block SMS messages with matching features through the operator interface, so that users cannot receive SMS messages with matching features, thus blocking the phishing SMS in the process of spreading.
[0082] DNS pollution blocking: Through the operator interface, the domain name resolution of the phishing website on the DNS server is modified to point to other IP addresses (such as the IP address of the anti-fraud warning site, etc.), and blocked when the user visits (at the end of the transmission).
[0083] Through the phishing website processing method in this embodiment, an effective closed loop from discovery to disposal is achieved, thereby improving the security of users' website access and protecting users' property safety.
[0084] The present disclosure provides a phishing website detection device 300, such as Figure 3 As shown, including:
[0085] The collection module 301 is configured to identify target websites and collect suspected phishing websites among the target websites.
[0086] The feature extraction module 302 is configured to extract features from suspected phishing websites to obtain one or more behavior features.
[0087] The calculation module 303 is configured to calculate the feature similarity corresponding to the suspected phishing website based on one or more behavior features.
[0088] The determination module 304 is configured to determine whether the suspected phishing website is a phishing website based on feature similarity.
[0089] Specifically, the identification module 301 can collect the URLs of suspected phishing websites through multiple different channels, such as through DNS servers and phishing SMS messages, and can collect domain names and IP addresses similar to phishing websites identified in history and identify them as suspected phishing websites. Usually, phishing websites also have some characteristics. For example, the URLs of regular websites usually start with "http: / / " or "https: / / ", while the URLs of phishing websites may be relatively simple, even containing only letters and numbers. In addition, the domain names of phishing websites are usually similar to regular websites, but there may be slight differences. They can be matched through historical detection records, collect URLs of suspected phishing websites from multiple channels, and identify the domain names and IP addresses of suspected phishing websites.
[0090] The feature extraction module 302 extracts features from the collected suspected phishing websites, and the extracted behavior features may include but are not limited to URL (uniform resource locator), page HTML (Hyper Text Markup) elements, HTTP (Hypertext Transfer Protocol) access features, etc. The calculation module 303 then calculates the feature similarity with the identified phishing URLs based on the extracted behavior features.
[0091] After the calculation module 303 calculates the feature similarity with the identified phishing website, the determination module 304 compares the feature similarity with the preset threshold. If the feature similarity reaches the preset threshold, the suspected phishing website can be determined to be a phishing website. In this way, the collected suspected phishing websites can be accurately judged to reduce misidentification. After the rough identification in step S101, the suspected phishing website is accurately identified, which can reduce the identification coverage of the phishing website and improve the accuracy of the identification.
[0092] As an optional implementation, the identification module 301 identifies the target website, and collecting suspected phishing websites from the target website includes at least one of the following:
[0093] (1) Perform domain name analysis on the target website through the domain name system server to obtain the IP address of the target website.
[0094] DNS server collection: When the domain name of a phishing website is accessed, DNS domain name resolution will be performed to obtain the real website IP address. The resolution record will be recorded by the DNS server responsible for resolution work. By analyzing the workplace network environment or the operator's DNS server resolution record, the domain name of the website IP address resolved by DNS is marked as a suspected phishing website domain name.
[0095] (2) Conduct batch detection of IP addresses of overseas public clouds to obtain IP addresses of suspected phishing websites.
[0096] Detection and collection of overseas public cloud IP addresses in the C segment: Since overseas public cloud service providers are more difficult to control than domestic cloud service providers, almost all phishing website servers are set up in overseas public clouds. Regular batch detection of overseas public cloud IPs is carried out, and phishing website IP addresses are identified through phishing website detection and analysis.
[0097] (3) Collect phishing text messages through different channels and extract the domain names of suspected phishing websites from the phishing text messages.
[0098] Phishing SMS collection: Phishing SMS are collected through customer service, offline feedback, operator feedback and other channels, and the domain names of suspected phishing websites are extracted from them.
[0099] (4) Perform association analysis on known phishing websites to obtain the domain names and IP addresses of suspected phishing sites associated with the known phishing websites.
[0100] As an optional implementation, the identification module 301 performs domain name analysis on the target website through a domain name system server, and obtaining the IP address of the target website includes:
[0101] When accessing the target website, the domain name of the target website is resolved through the domain name system server to obtain the IP address of the target website;
[0102] The IP address of the target website is matched with the domain name of a known phishing site. If there is a match, it is marked as a suspected phishing website.
[0103] As an optional implementation, the calculation module 303 includes:
[0104] A setting unit is configured to set a corresponding characteristic coefficient for each behavior characteristic; wherein the sum of the plurality of characteristic coefficients is 1;
[0105] The calculation unit is configured to perform a product operation on the feature coefficients corresponding to the multiple behavior features, and sum the results of the product operation to obtain the feature similarity.
[0106] Specifically, it is currently found that the vast majority of phishing websites use several similar sets of website templates for rapid website construction. Therefore, for such phishing websites with obvious rule characteristics, a rule engine detection method is applicable. This method extracts one or more behavioral features X of the website (such as URL, page HTML elements, HTTP access features, etc.) as the judgment criteria of the rule engine. Different feature coefficients α are specified according to the strength of the behavioral characteristics (the relevance to the judgment of phishing websites), and the sum of multiple feature coefficients is 1; among them, the feature coefficient α is equivalent to the weight of each behavioral feature, and different weights are assigned according to the influence of each behavioral feature. Multiply multiple behavioral features X by the feature coefficient α and sum them to obtain the feature similarity R. The formula is as follows:
[0107]
[0108] In this embodiment, the collected suspected phishing websites are subjected to feature similarity calculation, and if the feature similarity exceeds a preset threshold, they are identified as phishing websites.
[0109] As an optional implementation, the feature extraction module 302 extracts features from suspected phishing websites to obtain one or more behavior features including:
[0110] Feature extraction is performed on suspected phishing websites to obtain one or more behavioral features of uniform resource locator features (URL), page markup language element features (page HTML elements), and hypertext transfer protocol access features (HTTP access features).
[0111] As an optional implementation, the determination module 304 determines whether the suspected phishing website is a phishing website based on feature similarity, including:
[0112] The feature similarity is compared with the preset threshold, and if the feature similarity exceeds the preset threshold, it is identified as a phishing website. For example, if the feature similarity between a suspected phishing website and an identified phishing website reaches 60%, it can be determined to be a phishing website.
[0113] As an optional implementation, the phishing website detection device 300 further includes:
[0114] The association analysis module is configured to perform association analysis on the URLs that have been identified as phishing websites to obtain associated suspected phishing websites after the determination module 304 determines whether the suspected phishing website is a phishing website based on feature similarity.
[0115] The second feature extraction module is configured to extract features from the associated suspected phishing websites to obtain one or more second behavior features.
[0116] The second calculation module is configured to calculate the second feature similarity corresponding to the associated suspected phishing website based on one or more second behavior features.
[0117] The second determination module is configured to determine whether the associated suspected phishing website is a phishing website based on the second feature similarity.
[0118] Specifically, after detecting and confirming a phishing website, you can continue to detect websites associated with the phishing website, and also obtain the feature similarity of each associated website by calculating the feature similarity, and then determine whether the associated website is a phishing website. In this way, compared with traversing all target websites, the detection is more targeted, the associated phishing website can be detected quickly, and the detection timeliness is higher.
[0119] As an optional implementation manner, the URL of the phishing website includes the domain name and / or URL of the phishing website; the association analysis module performs association analysis on the URL that has been identified as the phishing website, and obtains the associated suspected phishing website in the following two ways:
[0120] (1) Perform association analysis on the domain names that have been identified as phishing websites to obtain associated suspected phishing websites.
[0121] (2) Perform association analysis on the IP addresses that have been identified as phishing websites to obtain associated suspected phishing websites.
[0122] Specifically, the association analysis module performs domain name association analysis including: obtaining the registration information of the phishing website, and querying the domain names registered at the same time or the historically registered domain names registered by the registrant according to the registration information, and classifying the domain names registered at the same time and the historically registered domain names as associated suspected phishing websites; obtaining the IP pointing information of the phishing website, and classifying the IP address pointed to by the IP pointing information as an associated suspected phishing website; obtaining the subdomain name of the phishing website, and classifying the subdomain name as an associated suspected phishing website; in response to the domain name of the phishing website being a wildcard domain name, clipping the wildcard domain name to the next level, and classifying the clipped second-level domain name as an associated suspected phishing website; obtaining the adjacent domain names of the phishing website by recursively detecting the domain names constructed by frequency connection, and classifying the adjacent domain names as an associated suspected phishing website.
[0123] The association analysis module performs IP address association analysis including: obtaining the current associated domain name and the historical associated domain name associated with the IP address that has been identified as a phishing website, and classifying the current associated domain name and the historical associated domain name as associated suspected phishing websites; obtaining other IP addresses with the same C segment as the IP address that has been identified as a phishing website, and identifying the websites that are open to access as associated suspected phishing websites.
[0124] The present disclosure also provides a phishing website processing device 400, such as Figure 4As shown, including:
[0125] The acquisition module 401 is configured to acquire the domain name or IP address of the phishing website detected by the phishing website detection method described in any one of the above embodiments;
[0126] The processing module 402 is configured to process the domain name or IP address of the phishing site; wherein the processing includes at least one of the following: shutting down the phishing website; intercepting phishing text messages sent by the phishing website; and blocking access to the phishing website.
[0127] The processing module 402 of the present disclosure blocks and prevents access to domain names or IP addresses that have been identified as phishing websites. According to the links through which phishing websites spread, blocking strategies can be divided into the following three types:
[0128] Shutdown of phishing websites: Block phishing websites at the source through the cloud service provider that owns the IP address of the phishing website.
[0129] Phishing SMS interception: Block SMS messages with matching features through the operator interface, so that users cannot receive SMS messages with matching features, thus blocking the phishing SMS in the process of spreading.
[0130] DNS pollution blocking: Through the operator interface, the domain name resolution of the phishing website on the DNS server is modified to point to other IP addresses (such as the IP address of the anti-fraud warning site, etc.), and blocked when the user visits (at the end of the transmission).
[0131] Through the phishing website processing method in this embodiment, an effective closed loop from detection to disposal is achieved, thereby improving the security of users' access to websites and protecting users' property safety.
[0132] like Figure 5 As shown, the phishing website detection and processing system of the present disclosure mainly includes a suspected phishing website collection module 501, a suspected phishing website detection module 502, a phishing website association analysis module 503, and a phishing website processing module 504. Among them, the suspected phishing website collection module 501 is used to collect suspected phishing websites through multiple different channels; the suspected phishing website detection module 502 is used to detect the collected suspected phishing websites and determine the phishing websites among them; the phishing website association analysis module 503 further performs association analysis on the determined phishing websites to find the phishing websites associated with them; finally, the phishing website processing module 504 performs the processing such as blocking, interception, and blocking, so as to realize a closed loop from detection to disposal.
[0133] In the technical solution disclosed herein, the acquisition, storage and application of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.
[0134] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.
[0135] Figure 6 A schematic block diagram of an example electronic device 600 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.
[0136] like Figure 6 As shown, the device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.
[0137] A number of components in the device 600 are connected to the I / O interface 605, including: an input unit 606, such as a keyboard, a mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a disk, an optical disk, etc.; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.
[0138] The computing unit 601 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning objective function algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 601 performs the various methods and processes described above, such as a phishing website detection method or a phishing website processing method. For example, in some embodiments, the phishing website detection method or the phishing website processing method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of the phishing website detection method or the phishing website processing method described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to execute the phishing website detection method or the phishing website processing method in any other appropriate manner (eg, by means of firmware).
[0139] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
[0140] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.
[0141] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0142] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).
[0143] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.
[0144] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.
[0145] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of this disclosure can be achieved, and this document is not limited here.
[0146] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.
Claims
1. A method for detecting phishing websites, characterized in that: include: Identify target websites and collect suspected phishing websites among the target websites; Extracting features of the suspected phishing website to obtain one or more behavioral features; Based on one or more of the behavioral features, calculate the feature similarity corresponding to the suspected phishing website; Determine whether the suspected phishing website is a phishing website based on the feature similarity.
2. The method according to claim 1, wherein: The identifying of the target website and collecting the suspected phishing websites in the target website includes at least one of the following: Performing domain name analysis on the target website through a domain name system server to obtain the IP address of the target website; Conduct batch detection of IP addresses of overseas public clouds to obtain the IP addresses of the suspected phishing websites; Collect phishing text messages through different channels, and extract the domain name of the suspected phishing website from the phishing text messages; Perform association analysis on known phishing websites to obtain the domain name and IP address of the suspected phishing site associated with the known phishing website.
3. The method according to claim 2, wherein: The performing domain name analysis on the target website through a domain name system server to obtain the IP address of the target website includes: When accessing the target website, the domain name of the target website is resolved through the domain name system server to obtain the IP address of the target website; The IP address of the target website is matched with the domain name of the known phishing site, and if there is a match, it is identified as the suspected phishing website.
4. The method according to claim 1, wherein: The calculating, based on one or more of the behavior features, the feature similarity corresponding to the suspected phishing website comprises: A corresponding characteristic coefficient is set for each of the behavioral characteristics; wherein the sum of the plurality of characteristic coefficients is 1; The feature coefficients corresponding to the plurality of behavior features are multiplied, and the results of the multiplication are summed to obtain the feature similarity.
5. The method according to claim 1 or 4, wherein: The feature extraction of the suspected phishing website to obtain one or more behavior features includes: Feature extraction is performed on the suspected phishing website to obtain one or more behavioral features of uniform resource locator features, page markup language element features, and hypertext transfer protocol access features.
6. The method according to claim 1 or 4, wherein: The determining whether the suspected phishing website is a phishing website based on the feature similarity includes: The feature similarity is compared with a preset threshold, and if the feature similarity exceeds the preset threshold, it is identified as the phishing website.
7. The method according to any one of claims 1 to 6, wherein: After determining whether the suspected phishing website is a phishing website based on the feature similarity, the method further includes: Performing correlation analysis on the URLs identified as the phishing websites to obtain correlated suspected phishing websites; Extracting features of the associated suspected phishing websites, and calculating second feature similarities corresponding to the associated suspected phishing websites based on the extracted one or more second behavior features; Determine whether the associated suspected phishing website is the phishing website based on the second feature similarity.
8. The method according to claim 7, wherein: The URL of the phishing website includes the domain name and / or URL of the phishing website; the association analysis of the URL identified as the phishing website to obtain the associated suspected phishing website includes at least one of the following: Performing association analysis on the domain name identified as the phishing website to obtain the associated suspected phishing website; An association analysis is performed on the IP address that has been identified as the phishing website to obtain the associated suspected phishing website.
9. The method according to claim 8, wherein: The association analysis of the domain name identified as the phishing website to obtain the associated suspected phishing website includes: Acquire the registration information of the phishing website, and query the domain name registered in the same period or the historically registered domain name registered by the registrant according to the registration information, and classify the domain name registered in the same period and the historically registered domain name as the associated suspected phishing website; Acquire the IP pointing information of the phishing website, and classify the IP address pointed to by the IP pointing information as the associated suspected phishing website; Obtaining a subdomain of the phishing website, and classifying the subdomain as the associated suspected phishing website; In response to the domain name of the phishing website being a wildcard domain name, the wildcard domain name is clipped to the next level up, and the clipped second-level domain name is classified as the associated suspected phishing website; The adjacent domain names of the phishing website are obtained by recursive detection of frequently constructed domain names, and the adjacent domain names are classified as the associated suspected phishing websites.
10. The method according to claim 8, wherein: The associated suspected phishing websites obtained by performing association analysis on the IP addresses identified as the phishing websites include: Acquire the currently associated domain name and the historically associated domain name associated with the IP address that has been identified as the phishing website, and classify the currently associated domain name and the historically associated domain name as the associated suspected phishing website; Other IP addresses having the same C segment as the IP address identified as the phishing website are obtained, and websites that are open to access are identified as the associated suspected phishing websites.
11. A method for processing phishing websites, characterized in that: include: Obtaining the domain name or IP address of the phishing website detected by the phishing website detection method according to any one of claims 1 to 10; Process the domain name or IP address of the phishing site; wherein the processing includes at least one of the following: shutting down the phishing website; intercepting phishing text messages sent by the phishing website; blocking access to the phishing website.
12. A phishing website detection device, characterized in that: include: an identification module, configured to identify target websites and collect suspected phishing websites from the target websites; A feature extraction module is configured to extract features from the suspected phishing website to obtain one or more behavior features; A calculation module, configured to calculate a feature similarity corresponding to the suspected phishing website based on the extracted one or more behavior features; The determination module is configured to determine whether the suspected phishing website is a phishing website based on the feature similarity.
13. The device according to claim 12, wherein: The identification module identifies the target website, and collecting suspected phishing websites from the target website includes at least one of the following: Performing domain name analysis on the target website through a domain name system server to obtain the IP address of the target website; Conduct batch detection of IP addresses of overseas public clouds to obtain the IP addresses of the suspected phishing websites; Collect phishing text messages through different channels, and extract the domain name of the suspected phishing website from the phishing text messages; Perform association analysis on known phishing websites to obtain the domain name and IP address of the suspected phishing site associated with the known phishing website.
14. The device according to claim 13, wherein: The identification module performs domain name analysis on the target website through a domain name system server to obtain the IP address of the target website, including: When accessing the target website, the domain name of the target website is resolved through the domain name system server to obtain the IP address of the target website; The IP address of the target website is matched with the domain name of the known phishing site, and if there is a match, it is identified as the suspected phishing website.
15. The device according to claim 12, wherein: The calculation module comprises: a setting unit configured to set a corresponding characteristic coefficient for each of the behavior characteristics; wherein the sum of the plurality of characteristic coefficients is 1; The calculation unit is configured to perform a product operation on the feature coefficients corresponding to the plurality of behavior features, and sum the results of the product operation to obtain the feature similarity.
16. The device according to claim 12 or 15, wherein: The feature extraction module extracts features from the suspected phishing website to obtain one or more behavior features including: Feature extraction is performed on the suspected phishing website to obtain one or more behavioral features of uniform resource locator features, page markup language element features, and hypertext transfer protocol access features.
17. The device according to claim 12 or 15, wherein: The determining module determines whether the suspected phishing website is a phishing website based on the feature similarity, including: The feature similarity is compared with a preset threshold, and if the feature similarity exceeds the preset threshold, it is identified as the phishing website.
18. The device according to any one of claims 12 to 17, wherein: Also includes: an association analysis module configured to perform association analysis on the URL identified as the phishing website to obtain an associated suspected phishing website after the determination module determines whether the suspected phishing website is a phishing website based on the feature similarity; A second feature extraction module is configured to extract features from the associated suspected phishing websites, and calculate a second feature similarity corresponding to the associated suspected phishing websites based on the extracted one or more second behavior features; The second determination module is configured to determine whether the associated suspected phishing website is the phishing website based on the second feature similarity.
19. The device according to claim 18, wherein The URL of the phishing website includes the domain name and / or URL of the phishing website; the association analysis module performs association analysis on the URL identified as the phishing website, and the associated suspected phishing website includes at least one of the following: Performing association analysis on the domain name identified as the phishing website to obtain the associated suspected phishing website; An association analysis is performed on the IP address that has been identified as the phishing website to obtain the associated suspected phishing website.
20. The device according to claim 19, wherein The association analysis module performs association analysis on the domain name identified as the phishing website, and obtains the associated suspected phishing website including: Acquire the registration information of the phishing website, and query the domain name registered in the same period or the historically registered domain name registered by the registrant according to the registration information, and classify the domain name registered in the same period and the historically registered domain name as the associated suspected phishing website; Acquire the IP pointing information of the phishing website, and classify the IP address pointed to by the IP pointing information as the associated suspected phishing website; Obtaining a subdomain of the phishing website, and classifying the subdomain as the associated suspected phishing website; In response to the domain name of the phishing website being a wildcard domain name, the wildcard domain name is clipped to the next level up, and the clipped second-level domain name is classified as the associated suspected phishing website; The adjacent domain names of the phishing website are obtained by recursive detection of frequently constructed domain names, and the adjacent domain names are classified as the associated suspected phishing websites.
21. The device according to claim 19, wherein The association analysis module performs association analysis on the IP address identified as the phishing website, and obtains the associated suspected phishing website including: Acquire the currently associated domain name and the historically associated domain name associated with the IP address that has been identified as the phishing website, and classify the currently associated domain name and the historically associated domain name as the associated suspected phishing website; Other IP addresses having the same C segment as the IP address identified as the phishing website are obtained, and websites that are open to access are identified as the associated suspected phishing websites.
22. A phishing website processing device, characterized in that: include: An acquisition module, configured to acquire the domain name or IP address of the phishing website detected by the phishing website detection method according to any one of claims 1 to 10; The processing module is configured to process the domain name or IP address of the phishing site; wherein the processing includes at least one of the following: shutting down the phishing website; intercepting phishing text messages sent by the phishing website; and blocking access to the phishing website.
23. An electronic device, comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 10.
24. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-10.
25. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 10.
Citation Information
Patent Citations
Fishing web page clustering method and device
CN103399912A
Multi-channel method for actively monitoring phishing websites based on behavior characteristics
CN106302438A
Phishing website detection method and device, equipment and computer readable storage medium
CN111756724A
Phishing website processing method and device, storage medium and electronic equipment
CN115085952A
Phishing website detection
US20210099484A1
