CN108052543A - A kind of similar account detection method of microblogging based on map analysis cluster - Google Patents
A kind of similar account detection method of microblogging based on map analysis cluster Download PDFInfo
- Publication number
- CN108052543A CN108052543A CN201711181758.XA CN201711181758A CN108052543A CN 108052543 A CN108052543 A CN 108052543A CN 201711181758 A CN201711181758 A CN 201711181758A CN 108052543 A CN108052543 A CN 108052543A
- Authority
- CN
- China
- Prior art keywords
- user
- similarity
- information
- sim
- account
- 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.)
- Granted
Links
Classifications
-
- 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
- G06F16/95—Retrieval from the web
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
-
- 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
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
Abstract
The invention discloses a kind of similar account detection method of microblogging based on map analysis cluster and multidimensional similarity calculation, particular content includes：S1. malice account identification problem is converted into user's similarity calculation problem；S2. user information is calculated into structure digraph by scheming；S3. using map analysis algorithm to user clustering；S4. consistency weight d, the user for filtering Sparse are introduced；S5. MDUS algorithms are introduced, similarity is calculated based on various dimensions information；S6. each dimensionality weight is calculated using analytic hierarchy process (AHP), obtains Weighted Similarity；S7. reptile obtains m user data, is tested in spark, inputs target user's information, obtains similar account set as suspicious malice account, the accuracy rate of MDUS algorithms is up to 80%.This method will be based on map analysis cluster and multidimensional similarity calculation is combined, and realizes the account number that quickly notes abnormalities, to safeguarding that social network sites stabilization has great importance.
Description
Technical field
The invention belongs to information technology fields, and in particular to a kind of micro- based on map analysis cluster and multidimensional similarity calculation
Win similar account detection method.It realizes the similar account of quick discovery microblogging, perceives malice group behavior, effectively identify network navy
Or reincarnation account, have great importance to social networks improvement.
Background technology
At present, the analytical technology of social networks is becoming the hot spot and trend of network technology research, academia and industry
Boundary proposes numerous studies scheme, including analysis user characteristics, user behavior pattern and network structure, pacifies for social networks
Entirely, privacy of user protection, network colony event monitoring etc. have important value.Domestic and international many universities and research institution are all herein
Field expands further investigation, external such as University of California Berkeley, Carnegie Mellon University；It is and Microsoft Research, clear
The units such as Hua Da, Peking University are the representatives of studies in China, some important achievements in research repeatedly appear in S＆P, CCS,
On the top-level meeting and periodical of the international information-securities such as USS, KDD, AAAI field and Data Mining, wherein there is hundreds of
It is related to social networks safety problem, the academic research more than thousand is related with social network user similitude.In current network
There are a collection of account numbers, they are concentrated in a certain period of time, carry out substantial amounts of malicious act.These account numbers may be attacker's wound
The a large amount of false account numbers built and the account number usurped, this kind of account should find and handle as early as possible, prevent to social network sites and user
Privacy causes security risk.However the manual examination and verification stage is remained in for the main monitoring means of this kind of account at present, therefore,
A kind of method for quickly detecting similar account number is conducive to efficiently safeguard the stability and security of social network space.
The content of the invention
The invention discloses a kind of similar accounts of microblogging calculated based on Spark Graph X map analysis clusters and various dimensions
Detection method carries out graphX map analysis clusters based on user basic information and behavioural characteristic, passes through MDUS in respective classes
(calculating similarity based on user's various dimensions information) algorithm, obtains similar account number sequence.Particular content includes：
S1. since the malice account number of batch has the similitude of height, the identification problem of malice account is converted into user
Similarity calculation problem obtains similar account set by similarity calculation, chooses topN (N can choose 3,5,10 etc.) and makees
For suspicious malice account, be conducive to network administrator and examined；
S2. microblog users information by large-scale parallel figure is calculated and carries out user's portrait, drawn a portrait including customer relationship
It draws a portrait with user behavior, builds user's concern relation digraph and microblogging forwarding relation digraph respectively；
S3. using digraph as data source, using Spark GraphX map analysis algorithm Connected Components,
It is connected based on the user in network to user clustering, it is generally recognized that it is divided into the similarity that a kind of user has bigger, therefore,
Data set to be tested will be used as in of a sort user with target user, so as to reduce answering for similarity calculation between mass users
Polygamy；
S4. consistency weight d is introduced, considers the bean vermicelli number m of user1, concern number m2And hair microblogging number m3With the user
The average value n of all users in the classification of placeiThe ratio between (i=1,2,3), by formulaObtain consistency weight d, mistake
It filters the user of Sparse (d ＜ α), solves caused by microblog users Deta sparseness that accuracy rate of testing result is not high to ask
Topic；
S5. after the user for filtering out Sparse, calculate in target user u and place classification between other users u '
Similarity Sim (u, u '), the calculating of similarity introduces MDUS algorithms, i.e., calculates similarity based on user's various dimensions information, will
Microblog users information is divided into four dimensions, and background information, blog article information, bean vermicelli concern information, comment forwarding information use respectively
Editing distance, tf-idf, LDA, cosine similarity algorithm calculate similarity；
S6. total similarity is calculated by the following formula
Sim (u, u ')=
w1Simbackgroud(u, u ')+w2Simtext(u, u ')+w3Simfang(u, u ')+w4Simtweet(u, u '), wherein w1+
w2+w3+w4=1, and w1, w2, w3, w4Value drawn by the layer discrimination matrix computations in analytic hierarchy process (AHP), finally by formula
Calculate Weighted Similarity.
S7. choose n (n ＞ 500) and organize k (k ＞ 100) the name beans vermicelli of the well-known user of Sina as similarity threshold training set,
The similarity Sim (u, u ') between account is calculated, and calculates the average value of each group of Sim (u, u ')And standard deviation sigma, by formulaObtain similarity threshold μ；
S8. m (m are obtained by reptile>100000) name microblog users data, are tested on spark, and input target is used
Family (u) information verifies the accuracy of MDUS algorithms.Inspection result is arranged according to the numerical values recited of similarity, similar account
For topN (N can use 3,5,10 etc.) in set as suspicious malice account, Detection accuracy reaches maximum in N=5.
Description of the drawings
Fig. 1 is the calculating process of MDUS algorithms；
Fig. 2 is holistic approach frame；
Specific embodiment
The similar account detection method of microblogging based on map analysis cluster and multidimensional information similarity calculation
S1. m (m are obtained at random by reptile>100000) name microblog users data are as initial data set, including user's
Background information, blog article information, bean vermicelli, concern information and comment, forwarding information；
S2. tested in spark platforms, the information of input target user (u) passes through large-scale together with m users
Parallel map analysis carries out user's portrait, draws a portrait including customer relationship and user behavior is drawn a portrait, and is respectively that each user builds pass
Note relation digraph and microblogging forwarding relation digraph；
S3. using digraph as data source, using Spark GraphX map analysis algorithm Connected Components,
User is clustered based on user's connection in network, it is generally recognized that it is divided into the similarity that a kind of user has bigger,
Therefore, testing data collection will be used as in of a sort all users with target user u, so as to reduce similarity between mass users
The complexity of calculating；
S4. the consistency weight d that testing data concentrates each user is calculated, considers the bean vermicelli number m of user1, concern number m2
And hair microblogging number m3With the average value n of all users in the categoryiThe ratio between (i=1,2,3), by formulaIt obtains
Consistency weight d, filters out Sparse (d<α, through cross validation, α=0.5) user, solve microblog users Sparse
The problem of accuracy rate of testing result caused by property is not high；S5. after the user for filtering out Sparse, respectively using editor away from
From, tf-idf, LDA, cosine similarity algorithm calculate user u and testing data and concentrate background information between each user u ', win
Literary information, bean vermicelli concern information, the similarity Sim for commenting on forwarding information four dimensionsbackgroud(u, u '), Simtext(u,
U '), Simfans(u, u '), Simtweet(u, u ')；
S6. total similarity is calculated by the following formula
Sim (u, u ')=
w1Simbackgroud(u, u ')+w2Simtext(u, u ')+w3Simfans(u, u ')+w4Simtweet(u, u '), wherein w1+
w2+w3+w4- 1, and w1, w2, w3, w4Value drawn by the layer discrimination matrix computations in analytic hierarchy process (AHP), due to the back of the body of user
Scape information is smaller including mailbox, real-name authentication role when calculating similarity, therefore is assigned to relatively low weights, conversely,
Microblogging text message is assigned to higher weights；
S7. using MDUS algorithms, similarity is calculated based on various dimensions information, user u and testing data are obtained with reference to weights
Concentrate the Weighted Similarity between each user u '；
S8. through Spark Distributed Calculations, obtain the similar account set of target user u, according to similarity numerical value by greatly to
It is small to be arranged, during due to similarity threshold μ=0.25, rate of accuracy reached to peak, therefore μ=0.25 is chosen, if similarity
Numerical value is more than similarity threshold, then labeled as similar account number.TopN (N can use 3,5,10 etc.) in set is as suspicious malice
Account, Detection accuracy reach maximum in N=5, therefore choose top5 as testing result, rate of accuracy reached to 80%.
Claims (1)
1. a kind of similar account number detection method of microblogging based on map analysis cluster, it is characterised in that：
S1. since the malice account number of batch has the similitude of height, it is similar that the identification problem of malice account is converted into user
Computational problem is spent, similar account set is obtained by similarity calculation, chooses topN as suspicious malice account；
S2. microblog users information is subjected to user's portrait by scheming to calculate parallel, is drawn including customer relationship portrait and user behavior
Picture, customer relationship portrait include concern, are concerned information, and behavior portrait includes comment, forwarding information, builds user's concern respectively
Relation digraph and microblogging forwarding relation digraph；
S3. using Spark GraphX map analysis algorithm Connected Components, based on user's connection pair in network
User clustering, it is generally recognized that be divided into the similarity that a kind of user has bigger, therefore, with target user in of a sort use
Family will be used as data set to be tested, so as to reduce the complexity of similarity calculation between mass users；；
S4. consistency weight d is introduced, considers bean vermicelli number m1, concern number m2 and the hair microblogging number m3 of user and the user place
The average value n of all users in classificationiThe ratio between, wherein i=1,2,3, by formulaObtain consistency weight d, mistake
Filter the Sparse i.e. user of d ＜ 0.5；
S5. it is similar between calculating target user u and other users u ' in the classification of place after the user for filtering out Sparse
Degree Sim (u, u '), the calculating of similarity introduces MDUS algorithms, i.e., similarity is calculated based on user's various dimensions information, by microblogging
User information is divided into four dimensions, background information, blog article information, bean vermicelli concern information, comment forwarding information, respectively using editor
Distance, tf-idf, LDA, cosine similarity algorithm calculate similarity；
S6. total similarity is calculated by the following formula
Sim (u, u ')=w1Simbaokgroud(u, u ')+W2Simtext(u, u ')+W3Simfan3(u, u ')+W4Simtweet(u, u '),
Wherein w1+w2+w3+w4=1, and w1, w2, w3, w4Value drawn by the layer discrimination matrix computations in analytic hierarchy process (AHP),
Weighted Similarity is finally calculated by formula；Wherein w1, w2, w3, w4Respectively background information, blog article information, bean vermicelli concern information,
Comment on the similarity weights of forwarding information；
S7. the k name beans vermicelli of the n groups well-known user of Sina are collected as similarity threshold training set, calculate the similarity between account
Sim (u, u '), and calculate the average value of each group of Sim (u, u ')And standard deviation sigma, by formulaObtain similitude
Threshold value μ；
S8. m microblog users data are obtained by reptile, inputs target user (u) information, if similarity numerical value is more than similitude
Threshold value μ, then labeled as suspicious malice account number.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711181758.XA CN108052543B (en) | 2017-11-23 | 2017-11-23 | Microblog similar account detection method based on graph analysis clustering |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711181758.XA CN108052543B (en) | 2017-11-23 | 2017-11-23 | Microblog similar account detection method based on graph analysis clustering |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108052543A true CN108052543A (en) | 2018-05-18 |
| CN108052543B CN108052543B (en) | 2021-02-26 |
Family
ID=62120388
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711181758.XA Active CN108052543B (en) | 2017-11-23 | 2017-11-23 | Microblog similar account detection method based on graph analysis clustering |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108052543B (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108876644A (en) * | 2018-05-24 | 2018-11-23 | 微梦创科网络科技（中国）有限公司 | A kind of similar account calculation method and device based on social networks |
| CN108898505A (en) * | 2018-05-28 | 2018-11-27 | 武汉斗鱼网络科技有限公司 | Recognition methods, corresponding medium and the electronic equipment of cheating clique |
| CN109040447A (en) * | 2018-08-01 | 2018-12-18 | 武汉斗鱼网络科技有限公司 | A kind of recognition methods, device, server and the storage medium of mobile phone wall |
| CN109460930A (en) * | 2018-11-15 | 2019-03-12 | 武汉斗鱼网络科技有限公司 | A kind of method and relevant device of determining adventure account |
| CN109587248A (en) * | 2018-12-06 | 2019-04-05 | 腾讯科技（深圳）有限公司 | User identification method, device, server and storage medium |
| CN109587523A (en) * | 2018-11-30 | 2019-04-05 | 武汉斗鱼网络科技有限公司 | A kind of recognition methods of false concern and relevant device |
| CN110598157A (en) * | 2019-09-20 | 2019-12-20 | 北京字节跳动网络技术有限公司 | Target information identification method, device, equipment and storage medium |
| CN110633734A (en) * | 2019-08-22 | 2019-12-31 | 成都信息工程大学 | Method for anomaly detection based on graph theory correlation theory |
| CN110876072A (en) * | 2018-08-31 | 2020-03-10 | 武汉斗鱼网络科技有限公司 | Batch registered user identification method, storage medium, electronic device and system |
| CN111047332A (en) * | 2019-11-13 | 2020-04-21 | 支付宝(杭州)信息技术有限公司 | Model training and risk identification method, device and equipment |
| CN112016934A (en) * | 2019-05-31 | 2020-12-01 | 慧安金科（北京）科技有限公司 | Method, apparatus, and computer-readable storage medium for detecting abnormal data |
| CN112100220A (en) * | 2020-09-22 | 2020-12-18 | 福建天晴在线互动科技有限公司 | System for realizing real-time monitoring of illegal account group |
| CN112148947A (en) * | 2020-09-28 | 2020-12-29 | 微梦创科网络科技（中国）有限公司 | Method and system for mining and reviewing users in batches |
| CN112800304A (en) * | 2021-01-08 | 2021-05-14 | 上海海事大学 | Microblog water army group detection method based on clustering |
| CN113378899A (en) * | 2021-05-28 | 2021-09-10 | 百果园技术(新加坡)有限公司 | Abnormal account identification method, device, equipment and storage medium |
| CN113806616A (en) * | 2021-08-16 | 2021-12-17 | 北京智慧星光信息技术有限公司 | Microblog user identification method, system, electronic equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101571870A (en) * | 2009-06-09 | 2009-11-04 | 北京航空航天大学 | User interest modeling method based on conceptual clustering |
| CN103118043A (en) * | 2011-11-16 | 2013-05-22 | 阿里巴巴集团控股有限公司 | Identification method and equipment of user account |
| US20130317910A1 (en) * | 2012-05-23 | 2013-11-28 | Vufind, Inc. | Systems and Methods for Contextual Recommendations and Predicting User Intent |
| CN103905532A (en) * | 2014-03-13 | 2014-07-02 | 微梦创科网络科技（中国）有限公司 | Microblog marketing account recognition method and system |
| CN103942489A (en) * | 2014-03-31 | 2014-07-23 | 中国科学院信息工程研究所 | Attack detection method and system on basis of cursor hidden scene |
| CN105376210A (en) * | 2014-12-08 | 2016-03-02 | 哈尔滨安天科技股份有限公司 | Account threat identification and defense method and system |
-
2017
- 2017-11-23 CN CN201711181758.XA patent/CN108052543B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101571870A (en) * | 2009-06-09 | 2009-11-04 | 北京航空航天大学 | User interest modeling method based on conceptual clustering |
| CN103118043A (en) * | 2011-11-16 | 2013-05-22 | 阿里巴巴集团控股有限公司 | Identification method and equipment of user account |
| US20130317910A1 (en) * | 2012-05-23 | 2013-11-28 | Vufind, Inc. | Systems and Methods for Contextual Recommendations and Predicting User Intent |
| CN103905532A (en) * | 2014-03-13 | 2014-07-02 | 微梦创科网络科技（中国）有限公司 | Microblog marketing account recognition method and system |
| CN103942489A (en) * | 2014-03-31 | 2014-07-23 | 中国科学院信息工程研究所 | Attack detection method and system on basis of cursor hidden scene |
| CN105376210A (en) * | 2014-12-08 | 2016-03-02 | 哈尔滨安天科技股份有限公司 | Account threat identification and defense method and system |
Non-Patent Citations (1)
| Title |
|---|
| 庄俊玺 等: "一种可信网络身份鉴别方案", 《北京工业大学学报》 * |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108876644B (en) * | 2018-05-24 | 2022-02-22 | 微梦创科网络科技（中国）有限公司 | Similar account calculation method and device based on social network |
| CN108876644A (en) * | 2018-05-24 | 2018-11-23 | 微梦创科网络科技（中国）有限公司 | A kind of similar account calculation method and device based on social networks |
| CN108898505A (en) * | 2018-05-28 | 2018-11-27 | 武汉斗鱼网络科技有限公司 | Recognition methods, corresponding medium and the electronic equipment of cheating clique |
| CN109040447A (en) * | 2018-08-01 | 2018-12-18 | 武汉斗鱼网络科技有限公司 | A kind of recognition methods, device, server and the storage medium of mobile phone wall |
| CN110876072B (en) * | 2018-08-31 | 2022-02-08 | 武汉斗鱼网络科技有限公司 | Batch registered user identification method, storage medium, electronic device and system |
| CN110876072A (en) * | 2018-08-31 | 2020-03-10 | 武汉斗鱼网络科技有限公司 | Batch registered user identification method, storage medium, electronic device and system |
| CN109460930A (en) * | 2018-11-15 | 2019-03-12 | 武汉斗鱼网络科技有限公司 | A kind of method and relevant device of determining adventure account |
| CN109460930B (en) * | 2018-11-15 | 2021-11-26 | 武汉斗鱼网络科技有限公司 | Method for determining risk account and related equipment |
| CN109587523A (en) * | 2018-11-30 | 2019-04-05 | 武汉斗鱼网络科技有限公司 | A kind of recognition methods of false concern and relevant device |
| CN109587523B (en) * | 2018-11-30 | 2021-05-28 | 武汉斗鱼网络科技有限公司 | False attention identification method and related equipment |
| CN109587248A (en) * | 2018-12-06 | 2019-04-05 | 腾讯科技（深圳）有限公司 | User identification method, device, server and storage medium |
| CN109587248B (en) * | 2018-12-06 | 2023-08-29 | 腾讯科技（深圳）有限公司 | User identification method, device, server and storage medium |
| CN112016934A (en) * | 2019-05-31 | 2020-12-01 | 慧安金科（北京）科技有限公司 | Method, apparatus, and computer-readable storage medium for detecting abnormal data |
| CN112016934B (en) * | 2019-05-31 | 2023-12-29 | 慧安金科（北京）科技有限公司 | Method, apparatus and computer readable storage medium for detecting abnormal data |
| CN110633734B (en) * | 2019-08-22 | 2022-08-19 | 成都信息工程大学 | Method for anomaly detection based on graph theory correlation theory |
| CN110633734A (en) * | 2019-08-22 | 2019-12-31 | 成都信息工程大学 | Method for anomaly detection based on graph theory correlation theory |
| CN110598157A (en) * | 2019-09-20 | 2019-12-20 | 北京字节跳动网络技术有限公司 | Target information identification method, device, equipment and storage medium |
| CN110598157B (en) * | 2019-09-20 | 2023-01-03 | 北京字节跳动网络技术有限公司 | Target information identification method, device, equipment and storage medium |
| CN111047332A (en) * | 2019-11-13 | 2020-04-21 | 支付宝(杭州)信息技术有限公司 | Model training and risk identification method, device and equipment |
| CN112100220B (en) * | 2020-09-22 | 2022-06-21 | 福建天晴在线互动科技有限公司 | System for realizing real-time monitoring of illegal account group |
| CN112100220A (en) * | 2020-09-22 | 2020-12-18 | 福建天晴在线互动科技有限公司 | System for realizing real-time monitoring of illegal account group |
| CN112148947A (en) * | 2020-09-28 | 2020-12-29 | 微梦创科网络科技（中国）有限公司 | Method and system for mining and reviewing users in batches |
| CN112148947B (en) * | 2020-09-28 | 2024-03-22 | 微梦创科网络科技（中国）有限公司 | Method and system for excavating and brushing users in batches |
| CN112800304A (en) * | 2021-01-08 | 2021-05-14 | 上海海事大学 | Microblog water army group detection method based on clustering |
| CN113378899A (en) * | 2021-05-28 | 2021-09-10 | 百果园技术(新加坡)有限公司 | Abnormal account identification method, device, equipment and storage medium |
| CN113806616A (en) * | 2021-08-16 | 2021-12-17 | 北京智慧星光信息技术有限公司 | Microblog user identification method, system, electronic equipment and storage medium |
| CN113806616B (en) * | 2021-08-16 | 2023-08-22 | 北京智慧星光信息技术有限公司 | Microblog user identification method, system, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108052543B (en) | 2021-02-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108052543A (en) | A kind of similar account detection method of microblogging based on map analysis cluster | |
| Ritter et al. | Weakly supervised extraction of computer security events from twitter | |
| CN106845265B (en) | Document security level automatic identification method | |
| US9870465B1 (en) | Apparatus, method and article to facilitate automatic detection and removal of fraudulent user information in a network environment | |
| Nizamani et al. | Detection of fraudulent emails by employing advanced feature abundance | |
| CN104899508B (en) | A kind of multistage detection method for phishing site and system | |
| Wu et al. | Social spammer and spam message co-detection in microblogging with social context regularization | |
| US9563770B2 (en) | Spammer group extraction apparatus and method | |
| Khan et al. | Segregating spammers and unsolicited bloggers from genuine experts on twitter | |
| CN108170692A (en) | A kind of focus incident information processing method and device | |
| Zafarani et al. | 10 bits of surprise: Detecting malicious users with minimum information | |
| EP3201782B1 (en) | Protected indexing and querying of large sets of textual data | |
| CN110134876B (en) | Network space population event sensing and detecting method based on crowd sensing sensor | |
| Riadi et al. | Log analysis techniques using clustering in network forensics | |
| CN108197474A (en) | The classification of mobile terminal application and detection method | |
| CN102324007A (en) | Method for detecting abnormality based on data mining | |
| Stuessy et al. | The importance of comprehensive phylogenetic (evolutionary) classification—a response to S chmidt‐L ebuhn's commentary on paraphyletic taxa | |
| Sarode et al. | Audit and Analysis of Impostors: An experimental approach to detect fake profile in online social network | |
| Yu et al. | A hybrid web log based intrusion detection model | |
| Kaja et al. | A two stage intrusion detection intelligent system | |
| CN109558555A (en) | Microblog water army detection method and detection system based on artificial immunity danger theory | |
| Raihan et al. | Human behavior analysis using association rule mining techniques | |
| CN105069158B (en) | Data digging method and system | |
| Kozik et al. | Packets tokenization methods for web layer cyber security | |
| WO2015074493A1 (en) | Method and apparatus for filtering out low-frequency click, computer program, and computer readable medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |