CN115599345A - Application security requirement analysis recommendation method based on knowledge graph - Google Patents
Application security requirement analysis recommendation method based on knowledge graph Download PDFInfo
- Publication number
- CN115599345A CN115599345A CN202211280931.2A CN202211280931A CN115599345A CN 115599345 A CN115599345 A CN 115599345A CN 202211280931 A CN202211280931 A CN 202211280931A CN 115599345 A CN115599345 A CN 115599345A
- Authority
- CN
- China
- Prior art keywords
- safety
- knowledge
- requirement
- security
- scene
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/10—Requirements analysis; Specification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
- G06F16/9024—Graphs; Linked lists
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses an application security requirement analysis recommendation method based on knowledge graph, which can search application adaptive security scene from application function, operation and running environment and output multiple security requirements associated with application security scene by establishing a knowledge graph library, searching security requirement knowledge graph and recommending security requirement analysis results. The knowledge graph reasoning operation is realized through law and regulation knowledge and application safety knowledge, the application safety requirement analysis speed can be greatly improved, and the knowledge dependence on safety requirement analysis personnel is reduced.
Description
Technical Field
The invention relates to the technical field of knowledge graphs, in particular to a knowledge graph-based application security requirement analysis recommendation method.
Background
Application requirements analysis is to develop a software product that meets the needs of the user, and for the requirements analysis, the needs of the user need to be known first. This is the fundamental condition for success of software development work. The application security requirements also need to be analyzed in the requirement analysis, the information security target can be realized through the security requirement analysis, the security quality of software is efficiently improved, and software bugs are reduced.
The application security requirement analysis is determined by the objective properties of the system, and is different from the general requirement analysis in that: the safety requirements are not based on the functional requirements and interests of the user, but rather are determined by the objective properties of the system. The existing safety demand analysis method has high requirements on the safety knowledge and law rule familiarity of safety demand analysts, the safety demand analysis implementation process is long, people are used for analysis, and the analysis tool only plays an auxiliary role.
Disclosure of Invention
The invention overcomes the defects of the prior art, provides the application safety requirement analysis method based on the knowledge graph, and can greatly improve the application safety requirement analysis speed and reduce the knowledge dependence on safety requirement analysis personnel by carrying out knowledge graph reasoning operation through legal and legal rules knowledge and application safety knowledge.
In order to solve the technical problems, the invention provides a knowledge graph-based application security requirement analysis recommendation method, which adopts the following technical scheme:
a knowledge graph-based application security requirement analysis recommendation method comprises the following steps:
s1: constructing a knowledge graph of safety requirements based on a service scene;
said S1 comprises the following steps of,
s11: collecting and identifying safety requirements;
collecting compliance security requirements and business security requirements;
s12: analyzing the collected safety requirements;
identifying the protected objects in each level through an Enterprise archive model;
forming a safety target by analyzing the safety attribute;
acquiring a safety control point by extracting safety requirements;
the protection object, the safety target and the safety control point are subjected to summary analysis to finally obtain safety requirements, and the safety requirements consist of safety baseline requirements and safety baseline requirements;
the safety baseline requirement class is a plurality of safety control points aiming at a certain protection object, and the safety baseline requirement items are specific safety control points.
S13: the safety requirements are corresponding to specific service scenes;
abstracting a large number of similar functions of the service system to form a service scene, and corresponding and associating the identified safety requirements with the service scene to form a safety requirement knowledge base of the service scene;
s14: constructing a scene safety requirement knowledge graph;
after the safety requirement knowledge base of each scene is obtained, the relation between all protected objects in the knowledge base is calculated, three element groups of 'entity-attribute-value' of application safety requirement knowledge are constructed, the three element groups are used as basic expression modes of facts, data are stored in a graph database, and a scene safety requirement knowledge graph is formed;
the entity is a service scene; the attribute is a safety baseline requirement class; the value is a safety baseline requirement item;
s2: searching safety requirements based on the knowledge graph;
identifying the entity, the entity attribute, the entity relationship and the entity relationship attribute of the subject domain in a specific safety requirement scene in the knowledge map library, mapping the knowledge of the application safety scene, and finally completing the display of the search result map by using the thesaurus of the application safety scene and a search engine algorithm.
Through the steps, the complex application safety requirement knowledge can be converted into an entity-attribute-value three-element group, the three-element group is used as a basic expression mode of a fact, data are stored in a graph database to form a scene safety requirement knowledge graph, the safety requirement scene knowledge graph is subjected to graphing and application of a safety scene word bank and a search engine algorithm, the safety requirement knowledge is finally output, and a search result is displayed through the graph.
The further technical scheme is as follows: the method for corresponding and associating the identified safety requirement with the service scene in S13 is specifically that a scene identification judgment is performed on the service system, and if the scene is identified, the safety requirement identified in S11 is corresponding and associated with the scene to form a safety requirement knowledge base of the scene;
if the scene is not identified, the identified security risk is converted into the security requirement in a threat modeling mode, is associated with the scene and is integrated into the overall security requirement knowledge base.
A further technical scheme is that, in the step S14 of constructing a scene security requirement knowledge graph, the specific way of calculating the relationship between each protected object in the knowledge base is as follows: and (3) using a ProjE algorithm, firstly calculating an incidence matrix of two known elements of the three elements, then performing distance calculation with the candidate entities, converting the prediction task into a sorting problem of the candidate entities, and putting each candidate entity into an undetermined triple for testing, thereby selecting an optimal entity.
Further technical solution is that after S14 constructs the scene security requirement knowledge graph, the following steps are performed before S2 searches for security requirements based on the knowledge graph:
s15: supplementing and fusing safety requirements;
collecting a large amount of safety knowledge, extracting the knowledge from safety requirement data in three formats of structured, semi-structured and unstructured, finally converting the extracted knowledge into a knowledge graph through the S11-S13, and supplementing and fusing the knowledge graph into the knowledge graph library;
the further technical scheme is that the specific method for extracting knowledge comprises the following steps:
aiming at structured data, mainly comprising data such as CVE (visual basic integrity) vulnerability data and CNVD (CNVD vulnerability data), carrying out data acquisition by using an MPP (maximum power point tracking) large-scale parallel processing model and constructing a regular expression for knowledge extraction;
aiming at semi-structured data, the data mainly have standard specification requirements and questionnaire data, a Hadoop big data technology is used for data acquisition, and then entities are extracted through regular expressions and data indexes;
aiming at unstructured data, mainly some text image data, a natural language processing technology and a POS-CBOW continuous bag-of-words model association algorithm based on semantic annotation are adopted to realize extraction of power grid resource knowledge entities and relations.
The further technical scheme is that the following steps are carried out after the safety requirement search based on the knowledge graph of S2:
s3: recommending application safety requirement analysis results;
the S3 specifically comprises the following steps:
s31: collecting application service scenes, searching application adaptation scenes from application functions, operation and running environments, and analyzing which service scenes a current application system consists of;
s32: the application security scene fusion, namely finding a plurality of similar applications and security scenes thereof for scene fusion;
s33: calculating and recommending, recommending commonly concerned application safety requirement knowledge points through a plurality of safety scenes, recommending to a user in a knowledge graph mode, determining the safety scenes, and recommending safety requirement terms of the safety scenes in other application systems in an ordering mode and a requirement strength mode.
And reasonably recommending according to the requirements such as the frequency of using the requirements in other service systems, the correlation of the service systems and the like. Optimal recommendations are considered on safety and cost efficiency, and strong safety requirements are pursued, so that construction cost and cloud efficiency of an application system are influenced.
Compared with the prior art, the invention has at least the following beneficial effects: by establishing a knowledge graph library, searching a safety requirement knowledge graph and recommending a safety requirement analysis result, a safety scene matched with an application can be searched from an application function, an operation environment and an operation environment, and a plurality of safety requirements related to the application safety scene are output. And outputting a safety requirement analysis result by taking a safety requirement which is commonly concerned by a plurality of application safety scenes as recommended content. The application safety requirement analysis speed is greatly improved, and the knowledge dependence on safety requirement analysis personnel is reduced.
Drawings
Fig. 1 is a schematic flow chart of a method for analyzing and recommending application security requirements based on a knowledge graph.
Fig. 2 is a schematic flow chart illustrating correspondence and association between security requirements and service scenarios.
Fig. 3 is a schematic diagram of the ProjE algorithm.
FIG. 4 is a diagram of a security requirement search based on a knowledge-graph.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the invention.
A method for analyzing and recommending application security requirements based on knowledge graph is disclosed, and referring to FIG. 1, the method comprises the following steps:
s1: constructing a knowledge graph of safety requirements based on a service scene;
said S1 comprises the following steps of,
s11: collecting and identifying safety requirements;
collecting compliance security requirements and business security requirements;
the requirement of meeting the safety mainly comprises the requirement that national policies, laws and regulations, standards and the like are set by corresponding people or organizations and the content is clear;
the service safety requirements are mainly safety requirements related to software service functions;
s12: analyzing the collected safety requirements;
identifying protected objects in various levels through an Enterprise archive model, wherein each level comprises: security protected objects, business functions, user roles, data, application components, supportive facilities;
forming a security target by analyzing security attributes, the security attributes comprising: confidentiality, integrity, availability, resistance to repudiation, traceability;
obtaining a security control point by extracting security requirements, the security control point comprising: business safety requirements, compliance requirements, and safety guarantee requirements;
the protection objects, the safety targets and the safety control points are subjected to summary analysis to finally obtain safety requirements, and the safety requirements consist of safety baseline requirement classes and safety baseline requirement items;
the safety baseline requirement class is a plurality of safety control points aiming at a certain protection object, and the safety baseline requirement item is a specific safety control point.
For example: the safety requirement of identity authentication is as follows: the method comprises an identity identification safety baseline, a password intensity safety baseline, an authentication communication encryption safety baseline and the like. The corresponding identity identification security baseline requirement items comprise: the safety requirement of the identity mark is that the identity mark is unique in the whole system, the identity mark is combined by pure numbers, and the identity mark can not be used as a safety requirement item such as an authentication field.
S13: the safety requirements are corresponding to specific service scenes;
the service functions frequently used by the service system are defined as service scenes. For example: a login identity verification scene, a service data search query scene, a product ordering payment scene and the like. The scenes are formed by abstracting a large number of similar functions of the business systems, the complex business systems can be simplified through the scenes, and the corresponding safety requirements can be quickly generated by utilizing the existing common method which accords with the safety requirements in the scenes.
After abstracting through similar functions of a large number of service systems, identifying service scenes, and associating the safety requirements identified in S11 with each service scene, as shown in fig. 2, if the safety requirements correspond to the identified scenes, directly corresponding and associating the safety requirements identified in S11 with the scenes to form a safety requirement knowledge base of the scenes.
If the scene is not identified, analyzing threat attack exposure surfaces generated by input and output of an application system and a data link in a threat modeling mode to identify the threat, namely judging whether the exposure surfaces have STRIDE threat risks or not, converting the identified security risks into security requirements after identifying the security risks, associating the security requirements with the scene, and integrating the security requirements into an integral security requirement knowledge base;
the STRIDE threat risk specifically includes fraud (Spoofing threatens), tampering (Tampering threatens), denial (declaration threatens), information disclosure (Information disclosure threatens), denial of service (Denial of service threatens), right-lifting (Elevation of priority threatens), and the like.
S14: constructing a scene safety requirement knowledge graph;
after the safety requirement knowledge base of each scene is obtained, the relation between all protection objects in the knowledge base is calculated, three element groups of 'entity-attribute-value' of application safety requirement knowledge are constructed, the three element groups are used as basic expression modes of facts, data are stored in a graph database, and all data stored in the graph database form an entity relation network to form a scene safety requirement knowledge graph.
The entity is a service scene; the attribute is a prior analysis safety baseline requirement class; the value is a safety baseline requirement item;
the specific way of calculating the relationship between the protected objects in the knowledge base is as follows: and (3) using a ProjE algorithm, firstly calculating an incidence matrix of two known elements of the three elements, then performing distance calculation with the candidate entities, converting the prediction task into a sorting problem of the candidate entities, and putting each candidate entity into an undetermined triple for testing, thereby selecting an optimal entity.
e is the scene, r is the entry, and W is the calculated appropriate demand
As shown in fig. 3, for a certain pending triplet { e, r, W }, where two elements, e and r, are known, the most suitable third element W is calculated. For example, when a triple of 'login security requirement' is constructed, the ProjE algorithm can accurately search entities which meet the application security requirement attribute according to the user authority and the login two elements, and has a relevant sequencing result to the entities, and finally, an optimal triple combination is obtained and stored in a knowledge map library.
S15: supplementing and fusing safety requirements;
collecting a large amount of safety knowledge, extracting the knowledge of safety requirement data in three formats of structural, semi-structural and non-structural, finally converting the extracted knowledge into a knowledge graph through the S11-S13, and supplementing and fusing the knowledge graph into the knowledge graph library;
specific methods for extracting knowledge aiming at different types of safety requirements are as follows:
aiming at structured data, mainly comprising data such as CVE (virtual video environment) vulnerability data and CNVD (CNVD vulnerability data), carrying out data acquisition by using an MPP (maximum Power parallel processor) model and constructing a regular expression for knowledge extraction;
aiming at semi-structured data, the data mainly have standard specification requirements and questionnaire data, a Hadoop big data technology is used for data acquisition, and then entities are extracted through regular expressions and data indexes;
aiming at unstructured data, mainly referring to some text image data, extracting power grid resource knowledge entities and relations by adopting a natural language processing technology and a POS-CBOW continuous bag-of-words model association algorithm based on semantic annotation;
s2: searching safety requirements based on the knowledge graph;
as shown in fig. 4, the topic domain entity, the entity attribute, the entity relationship and the entity relationship attribute in a specific security requirement scene in the knowledge map library are identified, the application security scene knowledge map is formed, and then the application security scene word library and the search engine algorithm are used to finally complete the search result map display;
in order to further optimize the solution, the embodiment of the present invention is further improved on the basis of the above embodiment, and the following steps are performed after S2:
s3: recommending application safety requirement analysis results;
s31: collecting application service scenes, searching application adaptation scenes from application functions, operation and running environments, and analyzing which service scenes a current application system consists of;
s32: the application security scene fusion, namely finding a plurality of similar applications and security scenes thereof for scene fusion;
the scenes analyzed by the same service function are matched with a plurality of scenes, the scenes have safety requirements which are mutually crossed, for example, the 'login authentication scene' and the 'order payment scene' both have a safety requirement baseline of 'encryption transmission', the 'encryption transmission' of the 'login authentication scene' requires ssl encryption transmission, the 'encryption transmission' of the 'order payment scene' requires ssl bidirectional authentication encryption transmission, and then the two similar safety requirements are fused to meet the requirement of a higher safety requirement or the aggregate of a plurality of safety requirements as the fused safety requirement.
S33: calculating and recommending, recommending commonly concerned application safety requirement knowledge points through a plurality of safety scenes, recommending to a user in a knowledge graph mode, determining the safety scenes, and recommending safety requirement terms of the safety scenes in other application systems in an ordering mode and a requirement strength mode.
For example, "two-factor authentication" has various security requirements, such as password + mobile phone short message, password + fingerprint, password + token, and the like. And reasonably recommending according to the frequency of the use of the requirements in other business systems, the related business systems and other protection requirements.
Although the invention has been described herein with reference to illustrative embodiments thereof, it should be understood that numerous other modifications and embodiments can be devised by those skilled in the art that will fall within the spirit and scope of the principles of this disclosure. More specifically, various variations and modifications are possible in the component parts and/or arrangements of the subject combination arrangement within the scope of the disclosure. In addition to variations and modifications in the component parts and/or arrangements, other uses will also be apparent to those skilled in the art.
Claims (6)
1. A knowledge graph-based application security requirement analysis recommendation method comprises the following steps:
s1: constructing a knowledge graph of safety requirements based on a service scene;
the S1 comprises the following steps:
s11: collecting and identifying safety requirements;
collecting compliance security requirements and business security requirements;
s12: analyzing the collected safety requirements;
identifying the protected objects in each level through an Enterprise archive model;
forming a safety target by analyzing the safety attribute;
acquiring a safety control point by extracting safety requirements;
the protection objects, the safety targets and the safety control points are subjected to summary analysis to finally obtain safety requirements, and the safety requirements consist of safety baseline requirement classes and safety baseline requirement items;
s13: the safety requirements are corresponding to specific service scenes;
abstracting a large number of similar functions of the service system to form a service scene, and corresponding and associating the identified safety requirements with the service scene to form a safety requirement knowledge base of the service scene;
s14: constructing a scene safety requirement knowledge graph;
after the safety requirement knowledge base of each scene is obtained, the relation between all protected objects in the knowledge base is calculated, three element groups of 'entity-attribute-value' of application safety requirement knowledge are constructed, the three element groups are used as basic expression modes of facts, data are stored in a graph database, and a scene safety requirement knowledge graph is formed;
the entity is a service scene; the attribute is a safety baseline requirement class; the value is a safety baseline requirement item;
s2: searching safety requirements based on the knowledge graph;
identifying the entity, entity attribute, entity relationship and entity relationship attribute of the subject domain in a specific security requirement scene in the knowledge map library, mapping the application security scene knowledge, and finally completing the display of the search result map by using the application security scene word library and a search engine algorithm.
2. The method for analyzing and recommending application security requirements based on a knowledge graph according to claim 1, wherein the method for corresponding and associating the identified security requirements with the service scenarios in S13 is specifically to perform scene identification judgment on the service system, and if the identified scenarios exist, correspond and associate the security requirements identified in S11 with the scenarios to form a security requirement knowledge base of the scenarios;
if the scene is not identified, the identified security risk is converted into the security requirement in a threat modeling mode, is associated with the scene and is integrated into the overall security requirement knowledge base.
3. The method for analyzing and recommending application security requirements based on a knowledge graph according to claim 1, wherein the specific way of calculating the relationship between each protected object in the knowledge base in S14 is as follows: and (3) using a ProjE algorithm, firstly calculating an incidence matrix of two known elements of the three elements, then performing distance calculation with the candidate entities, converting the prediction task into a sorting problem of the candidate entities, and putting each candidate entity into an undetermined triple for testing, thereby selecting an optimal entity.
4. The method for analyzing and recommending application security requirements based on knowledge graph according to claim 1, wherein the following steps are performed after S14 constructing the scene security requirement knowledge graph and before S2 searching for security requirements based on knowledge graph:
s15: supplementing and fusing safety requirements;
collecting a large amount of safety knowledge, extracting the knowledge of safety requirement data in three formats of structural, semi-structural and non-structural, finally converting the extracted knowledge into a knowledge map through the S11-S13, and supplementing and fusing the knowledge map into the knowledge map library.
5. The application security requirement analysis recommendation method based on the knowledge graph as claimed in claim 4, wherein the specific method of knowledge extraction is as follows:
aiming at structured data, mainly comprising data such as CVE (visual basic integrity) vulnerability data and CNVD (CNVD vulnerability data), carrying out data acquisition by using an MPP (maximum power point tracking) large-scale parallel processing model and constructing a regular expression for knowledge extraction;
aiming at semi-structured data, the data mainly have standard specification requirements and questionnaire data, a Hadoop big data technology is used for data acquisition, and then entities are extracted through regular expressions and data indexes;
aiming at unstructured data, mainly some text image data, a natural language processing technology and a POS-CBOW continuous bag-of-words model association algorithm based on semantic annotation are adopted to realize extraction of power grid resource knowledge entities and relations.
6. The method for analyzing and recommending application security requirements based on knowledge-graph according to claim 1, wherein the step S2 of searching security requirements based on knowledge-graph is followed by the steps of:
s3: recommending application safety requirement analysis results;
the S3 specifically comprises the following steps:
s31: collecting application service scenes, searching application adaptation scenes from application functions, operation and running environments, and analyzing which service scenes a current application system consists of;
s32: the application security scene fusion, namely finding a plurality of similar applications and security scenes thereof for scene fusion;
s33: calculating and recommending, recommending commonly concerned application safety requirement knowledge points through a plurality of safety scenes, recommending to a user in a knowledge graph mode, determining the safety scenes, and recommending safety requirement terms of the safety scenes in other application systems in an ordering mode and a requirement strength mode.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211280931.2A CN115599345A (en) | 2022-10-19 | 2022-10-19 | Application security requirement analysis recommendation method based on knowledge graph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211280931.2A CN115599345A (en) | 2022-10-19 | 2022-10-19 | Application security requirement analysis recommendation method based on knowledge graph |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115599345A true CN115599345A (en) | 2023-01-13 |
Family
ID=84848839
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211280931.2A Pending CN115599345A (en) | 2022-10-19 | 2022-10-19 | Application security requirement analysis recommendation method based on knowledge graph |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115599345A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116737111A (en) * | 2023-08-14 | 2023-09-12 | 深圳海云安网络安全技术有限公司 | Safety demand analysis method based on scenerization |
-
2022
- 2022-10-19 CN CN202211280931.2A patent/CN115599345A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116737111A (en) * | 2023-08-14 | 2023-09-12 | 深圳海云安网络安全技术有限公司 | Safety demand analysis method based on scenerization |
| CN116737111B (en) * | 2023-08-14 | 2023-10-13 | 深圳海云安网络安全技术有限公司 | Safety demand analysis method based on scenerization |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109816397B (en) | Fraud discrimination method, device and storage medium | |
| CN109347801B (en) | Vulnerability exploitation risk assessment method based on multi-source word embedding and knowledge graph | |
| Patil et al. | A methodical overview on phishing detection along with an organized way to construct an anti-phishing framework | |
| US20200004989A1 (en) | Systems and methods of determining compromised identity information | |
| CN108090351B (en) | Method and apparatus for processing request message | |
| CN112165462A (en) | Attack prediction method and device based on portrait, electronic equipment and storage medium | |
| CN104504335B (en) | Fishing APP detection methods and system based on page feature and URL features | |
| CN109831459B (en) | Method, device, storage medium and terminal equipment for secure access | |
| CN112699382B (en) | Internet of things network security risk assessment method and device and computer storage medium | |
| Stepanova et al. | Ontology-based big data approach to automated penetration testing of large-scale heterogeneous systems | |
| Karim et al. | Phishing detection system through hybrid machine learning based on URL | |
| CN110532480B (en) | Knowledge graph construction method for recommending human-read threat information and threat information recommendation method | |
| TW202121329A (en) | Method and apparatus for evaluating risk of leakage of private data | |
| Aydin et al. | Using attribute-based feature selection approaches and machine learning algorithms for detecting fraudulent website URLs | |
| Zhou et al. | CTI view: APT threat intelligence analysis system | |
| CN115599345A (en) | Application security requirement analysis recommendation method based on knowledge graph | |
| Igbekele et al. | Research trends on CAPTCHA: A systematic literature | |
| Ahmed et al. | A framework for phishing attack identification using rough set and formal concept analysis | |
| Dangwal et al. | Feature selection for machine learning-based phishing websites detection | |
| US20230039039A1 (en) | Process for determining a degree of data exposure | |
| Melshiyan et al. | Information Security Audit Using Open Source Intelligence Methods | |
| CN112258009B (en) | Intelligent government affair request processing method | |
| Yang et al. | TAPESTRY: A blockchain based service for trusted interaction online | |
| Jansi | An Effective Model of Terminating Phishing Websites and Detection Based On Logistic Regression | |
| Kumar et al. | Brain storm optimization based association rule mining model for intelligent phishing URLs websites detection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |